Stefano Soatto

One-Shot Integral Invariant Shape Priors for Variational Segmentation (2008)

In modeling complex visual phenomena one can employ rich models that characterize the global statistics of images, or choose simple classes of models to represent the local statistics of a...

Siddharth Manay, Daniel Cremers, Anthony Yezzi, Stefano Soatto

We match shapes, even under severe deformations, via a smooth re-parametrization of their integral invariant signatures. These robust signatures and correspondences are the foundation of a shape...

UCLA-CSD-TR#020001 Editable Dynamic Textures (2008)

3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination (2008)

We present a simple and efficient algorithm for modifying the temporal behavior of “dynamic textures,” i.e. sequences of images that exhibit some form of temporal regularity, such as flowing...

Hailin Jin, Dejun Wang, Daniel Cremers, Emmanuel Prados, Anthony Yezzi, Stefano Soatto

lighting and appearance reconstruction. We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from...

Moving Forward in Structure From Motion (2008)

Andrea Vedaldi, Gregorio Guidi, Stefano Soatto

It is well-known that forward motion induces a large number of local minima in the instantaneous least-squares reprojection error. This is caused in part by singularities in the error landscape...

Combining Topological and Geometric Features of Mammograms to Detect Masses (2008)

Byung-woo Hong, Matthew Mellor, Stefano Soatto, Michael Brady

Abstract. This paper presents a novel method for detecting masses in mammograms. Both topological (salience) and geometric (primarily texture) are used as features to characterise. Experimental...

A Complexity-Distortion Approach to Joint Pattern Alignment (2008)

A Study of Face Recognition as People Age (2008)

Image Congealing (IC) is a non-parametric method for the joint alignment of a collection of images affected by systematic and unwanted deformations. The method attempts to undo the deformations by...

Haibin Ling, Stefano Soatto, Narayanan Ramanathan, David W. Jacobs

In this paper we study face recognition across ages within a real passport photo verification task. First, we propose using the gradient orientation pyramid for this task. Discarding the gradient...

One-Shot Integral Invariant Shape Priors for Variational Segmentation ⋆ (2008)

Siddharth Manay, Daniel Cremers, Anthony Yezzi, Stefano Soatto

Abstract. We match shapes, even under severe deformations, via a smooth reparametrization of their integral invariant signatures. These robust signatures and correspondences are the foundation of a...

This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE IEEE TRANSACTION OF PATTERN RECO (2008)

Paolo Favaro, Stefano Soatto, Martin Burger, Stanley J. Osher

Abstract — Defocus can be modeled as a diffusion process and represented mathematically using the heat equation, where image blur corresponds to the diffusion of heat. This analogy can be extended...

Correspondence Transfer for the Registration of Multimodal Images (2008)

Zhao Yi, Stefano Soatto

Gene expression data provide information on the location where certain genes are active; in order for this to be useful, such a location must be registered to an anatomical atlas. Because gene...

Dynamical Models for Human Gait Synthesis (2008)

Alessandro Bissacco, Payam Saisan, Stefano Soatto

We present a novel approach to modeling human gaits such as walking and running. We represent the trajectories of a certain number of salient features on the human body as the output of a dynamical...

Hailin Jin, Anthony J. Yezzi, Yen-hsi Tsai, Li-tien Cheng, Stefano Soatto

ReceivedMay3,2002;accepted(inrevisedform)September14,2002

Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation (2008)

Dejun Wang, Emmanuel Prados, Stefano Soatto

We address the multi-view shape from shading problem, that is the recovery of 3-D shape, lighting configuration and surface albedo from multiple calibrated views. Previous approaches to this problem...

Real-time Virtual Object Insertion (2008)

Paolo Favaro, Hailin Jin, Stefano Soatto

We present a system to insert virtual objects into real image sequences in real time. The system consists of offthe-shelf hardware (a camera connected to a Pentium PC) and software to (a)...

On the Distance Between Non-stationary Time Series (2008)

Time Warping Under Dynamic Constraints (2008)

Comparing time series is a problem of critical importance in a broad range of applications, from data mining (searching for temporal “patterns ” in historical data), to speech recognition...

Michalis Raptis, Matteo Bustreo, Stefano Soatto

Abstract. Action and event recognition from video require comparing temporal sequences of images, or of intermediate representations derived from them. Such a comparison should be insensitive to...

Abstract Region matching with missing parts * (2008)

Ro Duci, Anthony J. Yezzi, Sanjoy K. Mitter, Stefano Soatto

We present a variational approach to the problem of registering planar shapes despite missing parts. Registration is achieved through the evolution of a partial differential equation that...

Applications of Hybrid System Identification in Computer Vision (2008)

René Vidal, Stefano Soatto

Abstract — In this expository paper we illustrate the use of filtering and identification-theoretic techniques in a number of problems in computer vision. We first demonstrate how linear system...

Abstract (2008)

Alessandro Bissacco, Stefano Soatto, Ming-hsuan Yang

We consider the problem of detecting humans and classifying their pose from a single image. Specifically, our goal is to devise a statistical model that simultaneously answers two questions: 1) is...

A geometric framework for dynamic vision (2008)

3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination (2008)

This thesis explores the problem of inferring information about the three-dimensional world from its projections onto a camera (images). Among all visual cues, we do not address "pictorial" ones,...

Jin, Hailin, Cremers, Daniel, Wang, Dejun, Prados, Emmanuel, Yezzi, Anthony, Soatto, Stefano

We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can...

3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination (2008)

Jin, Hailin, Cremers, Daniel, Wang, Dejun, Prados, Emmanuel, Yezzi, Anthony, Soatto, Stefano

We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can...

Flexible Dictionaries for Action Classification (2008)

Raptis, Michalis, Wnuk, Kamil, Soatto, Stefano

We present a simple approach to action classification which constructs a vector quantization of primitive motions from time series data corresponding to relative limb position estimates. The temporal...

Flexible Dictionaries for Action Classification (2008)

Raptis, Michalis, Wnuk, Kamil, Soatto, Stefano

We present a simple approach to action classification which constructs a vector quantization of primitive motions from time series data corresponding to relative limb position estimates. The temporal...

Stereoscopic Shading: Integrating Multi-frame Shape Cues in a Variational Framework (2007)

Hailin Jin Anthony, Anthony Yezzi, Stefano Soatto

We address the problem of integrating multi-frame stereo and shading cues within the framework of optimization in the innite-dimensional space of piecewise smooth surfaces. Cue integration then...

Recursive 3D Visual Motion Estimation Using Subspace Constraints (2007)

René Vidal, Stefano Soatto, S. Shankar Sastry

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion constraint and the perspective map. The time derivative...

Abstract (2007)

We study the problem of estimating the motion of independently moving objects observed by a moving perspective camera. We show that infinitesimal image measurements corresponding to independent...

2003 Kluwer Academic Publishers. Manufactured in The Netherlands. Deformotion: Deforming Motion, Shape Average and the Joint Registration and Approximation of Structures in Images (2007)

Anthony J. Yezzi, Stefano Soatto

Abstract. What does it mean for a deforming object to be "moving"? How can we separate the overall motion (a finite-dimensional group action) from the more general deformation (a...

Abstract (2007)

René Vidal, Stefano Soatto

We present a geometric approach for the analysis of dynamic scenes containing multiple rigidly moving objects seen in two perspective views. Our approach exploits the algebraic and geometric...

c ○ 2003 Kluwer Academic Publishers. Manufactured in The Netherlands. Dynamic Textures (2007)

Gianfranco Doretto, Alessandro Chiuso, Ying Nian Wu, Stefano Soatto

Abstract. Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a novel...

SNIPPETS OF SYSTEM IDENTIFICATION IN COMPUTER VISION (2007)

Stefano Soatto, Ro Chiuso

Abstract: In this paper we illustrate the use of identification-theoretic techniques in computer vision, and hint at some open problems.

z (2007)

Alessandro Bissacco, Alessandro Chiuso, Yi Ma, Stefano Soatto

We pose the problem of recognizing different types of human gait in the space of dynamical systems where each gait is represented. Established techniques are employed to track a kinematic model of a...

y (2007)

Motion from "X " by Compensating "Y" (2007)

motion We develop an efficient algorithm to track point features supported by image patches undergoing affine deformations and changes in illumination. The algorithm is based on an explicit...

Beyond Point Features Integrating Photometry and Geometry in Space and Time: A Semi-direct Approach to Structure From Motion (2007)

A unified framework for motion estimation from image sequences by compensating for the image-motion of a point, a line or a plane

Paolo Favaro, Hailin Jin, Stefano Soatto

dense shape, image mosaics. Reconstructing three-dimensional structure and motion is often decomposed into two steps: point feature correspondence and three-dimensional reconstruction. This...

Real-time Virtual Object Insertion (2007)

Paolo Favaro, Hailin Jin, Stefano Soatto

We present a system to insert virtual objects into real image sequences in real time. The system consists of offthe-shelf hardware (a camera connected to a Pentium PC) and software to (a)...

m (2007)

Stefano Soatto, Alessandro Chiuso

Technical Report UCLA-CSD 010001, March 6, 2000 We present a technique for reducing the dimensionality of a stationary time series with an arbitrary covariance sequence. This problem is solved in...

y (2007)

Alessandro Chiuso, Roger Brockett, Stefano Soatto

\Structure From Motion " (SFM) refers to the problem of estimating spatial properties of a threedimensional scene from the motion of its projection onto a two-dimensional surface, such as...

z (2007)

Heartbeat of a Nest: Using Imagers as Biological Sensors (2007)

Computer Vision. The necessary and sucient conditions for being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satised in practice. What...

y (2007)

Ruggero Frezza, Giorgio Picci, Stefano Soatto, Padova Italy

We address the problem of following an unknown planar contour with a nonholonomic vehicle based on visual feedback. The control task is to keep a point of the vehicle as close as possible to the...

Ahmadian, Shaun, Ko, Teresa, Coe, Sharon, Hamilton, M P, Rahimi, Mohammad, Soatto, Stefano, ...

We present a scalable end-to-end system for vision-based monitoring of a biological phenomenon. Our system enables automated analysis of thousands of images, where manual processing would be...

Evaluation of Imagers in a Biological Sensing Deployment (2007)

Degges, Joey, Ahmadian, Shaun, Coe, Sharon, Ko, Teresa, Hicks, John, Rahimi, Mohammed, ...

This poster presents the most recent deployment of wireless Cyclops camera nodes in the nest boxes of the James Reserve, and the various vision techniques used to analyze the acquired data. This has...

Exploring Tradeoffs in Accuracy, Energy and Latency of SIFT in Wireless Camera Networks (2007)

Ko, Teresa, Charbiwala, Zainul Mohammed, Ahmadian, Shaun, Rahimi, Mohammed, Srivastava, Mani B., Soatto, Stefano, ...

Advances in DSP technology create important avenues of research for embedded vision. One such avenue is the investigation of tradeoffs amongst system parameters which affect the energy, accuracy, and...

Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks (2007)

Ko, Teresa, Charbiwala, Zainul Mohammed, Ahmadian, Shaun, Rahimi, Mohammed, Srivastava, Mani B., Soatto, Stefano, ...

Advances in DSP technology create important avenues of research for embedded vision. One such avenue is the investigation of tradeoffs amongst system parameters which affect the energy, accuracy, and...

Exploring tradeoffs in accuracy, energy and latency of scale invariant feature transform in wireless camera networks (2007)

Teresa Ko, Zainul M. Charbiwala, Shaun Ahmadian, Mohammad Rahimi, Mani B. Srivastava, Stefano Soatto, ...

Advances in DSP technology create important avenues of research for embedded vision. One such avenue is the investigation of tradeoffs amongst system parameters which affect the energy, accuracy, and...

S.: Detecting humans via their pose (2007)

Alessandro Bissacco, Ming-hsuan Yang, Stefano Soatto

We consider the problem of detecting humans and classifying their pose from a single image. Specifically, our goal is to devise a statistical model that simultaneously answers two questions: 1) is...

Classification and recognition of dynamical models: the role of phase, independent components, kernels and optimal transport (2007)

Ro Bissacco, Ro Chiuso, Senior Member, Stefano Soatto

Abstract—We address the problem of performing decision tasks and, in particular, classification and recognition in the space of dynamical models in order to compare time series of data. Motivated...

J Math Imaging Vis (2007) 29: 219–234 DOI 10.1007/s10851-007-0030-9 Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images (2007)

Hailin Jin, Anthony J. Yezzi, Stefano Soatto, H. Jin, A. J. Yezzi, S. Soatto

Abstract We address the problem of estimating the shape and appearance of a scene made of smooth Lambertian surfaces with piecewise smooth albedo. We allow the scene to have self-occlusions and...

Control Theory and Fast Marching Methods for Brain Connectivity Mapping (2006)

Prados, Emmanuel, Lenglet, Christophe, Pons, Jean-Philippe, Wotawa, Nicolas, Deriche, Rachid, Faugeras, Olivier, ...

We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance...

Adventures in Automating Ecological Image Analysis (TER 3) (2006)

Brian Fulkerson, Stefano Soatto, Mike Allen, Mike Taggart, Michael Hamilton

As sensor networks become widely deployed in ecological settings, imaging is increasingly becoming an integral component of the system. Often, ecologists are interested in meta-information about the...

Control Theory and Fast Marching Methods for Brain Connectivity Mapping (2006)

Prados, Emmanuel, Lenglet, Christophe, Pons, Jean-Philippe, Wotawa, Nicolas, Deriche, Rachid, Faugeras, Olivier, ...

We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance...

Control Theory and Fast Marching Methods for Brain Connectivity Mapping (2006)

Prados, Emmanuel, Lenglet, Christophe, Pons, Jean-Philippe, Wotawa, Nicolas, Deriche, Rachid, Faugeras, Olivier, ...

We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance...

Dynamic Vision for Control (2006)

Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation (2006)

The goal of this project was to develop analytical and computational tools to make vision a viable sensor for the purpose of control. In order for unmanned vehicles to interact with a complex,...

Byung-woo Hong, Emmanuel Prados, Stefano Soatto, Luminita Vese

This paper presents a shape representation and a variational framework for the construction of diffeomorphisms that establish “meaningful ” correspondences between images, in that they preserve...

Integral invariants for shape matching (2006)

Siddharth Manay, Daniel Cremers, Byung-woo Hong, Anthony J. Yezzi, Stefano Soatto

Abstract—For shapes represented as closed planar contours, we introduce a class of functionals which are invariant with respect to the Euclidean group and which are obtained by performing integral...

Dynamic shape and appearance models (2006)

J Math Imaging Vis 25: 341–352, 2006 c ○ 2006 Springer Science + Business Media, LLC. Manufactured in The Netherlands. DOI: 10.1007/s10851-006-7249-8 Harmonic Embeddings for Linear Shape Analysis (2006)

Abstract—We propose a model of the joint variation of shape and appearance of portions of an image sequence. The model is conditionally linear, and can be thought of as an extension of active...

Alessandro Duci, Anthony Yezzi, Stefano Soatto, Kelvin Rocha

Abstract. We present a novel representation of shape for closed contours in R 2 or for compact surfaces in R 3 explicitly designed to possess a linear structure. This greatly simplifies linear...

Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation (2006)

Byung-woo Hong, Emmanuel Prados, Stefano Soatto, Luminita Vese

This paper presents a shape representation and a variational framework for the construction of diffeomorphisms that establish “meaningful ” correspondences between images, in that they preserve...

Control Theory and Fast Marching Techniques for Brain Connectivity Mapping (2006)

Emmanuel Prados, Christophe Lenglet, Nicolas Wotawa, Rachid Deriche, Olivier Faugeras, Stefano Soatto

We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance...

Viewpoint induced deformation statistics and the design of viewpoint invariant features: Singularities and occlusions (2006)

Int J Comput Vis DOI 10.1007/s11263-007-0055-y 3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination (2006)

Abstract. We study the set of domain deformations induced on images of three-dimensional scenes by changes of the vantage point. We parametrize such deformations and derive empirical statistics on...

Hailin Jin, Daniel Cremers, Dejun Wang, Emmanuel Prados, Anthony Yezzi, Stefano Soatto, ...

Abstract We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our...

Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation (2006)

Byung-woo Hong, Emmanuel Prados, Stefano Soatto, Luminita Vese

This paper presents a shape representation and a variational framework for the construction of diffeomorphisms that establish “meaningful ” correspondences between images, in that they preserve...

Viewpoint invariance for non-planar scenes (2006)

Control Theory and Fast Marching Techniques for Brain Connectivity Mapping (2006)

Most local feature detectors/descriptors implicitly assume that the scene is (locally) planar, an assumption that is violated at surface discontinuities. We show that this restriction is, at least in...

Prados, Emmanuel, Lenglet, Christophe, Pons, Jean-Philippe, Wotawa, Nicolas, Deriche, Rachid, Faugeras, Olivier, ...

We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance...

Control Theory and Fast Marching Techniques for Brain Connectivity Mapping (2006)

Prados, Emmanuel, Lenglet, Christophe, Pons, Jean-Philippe, Wotawa, Nicolas, Deriche, Rachid, Faugeras, Olivier, ...

We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance...

Méthode de ``Fast Marching'' générique pour le ``Shape From Shading'' (2006)

Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation (2006)

Nous développons une méthode numérique permettant de résoudre en un seul passage les équations aux dérivées partielles associées au problème du Shape From Shading générique [4, 5]. Notre...

Hong, Byung-Woo, Prados, Emmanuel, Soatto, Stefano, Vese, Luminita

This paper presents a shape representation and a variational framework for the construction of diffeomorphisms that establish ?meaningful? correspondences between images, in that they preserve the...

Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation (2006)

Wang, Dejun, Prados, Emmanuel, Soatto, Stefano

We address the multi-view shape from shading problem, that is the recovery of 3-D shape, lighting configuration and surface albedo from multiple calibrated views. Previous approaches to this problem...

Méthode de ``Fast Marching'' générique pour le ``Shape From Shading'' (2006)

Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation (2006)

Nous développons une méthode numérique permettant de résoudre en un seul passage les équations aux dérivées partielles associées au problème du Shape From Shading générique [4, 5]. Notre...

Hong, Byung-Woo, Prados, Emmanuel, Soatto, Stefano, Vese, Luminita

This paper presents a shape representation and a variational framework for the construction of diffeomorphisms that establish ?meaningful? correspondences between images, in that they preserve the...

Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation (2006)

Wang, Dejun, Prados, Emmanuel, Soatto, Stefano

We address the multi-view shape from shading problem, that is the recovery of 3-D shape, lighting configuration and surface albedo from multiple calibrated views. Previous approaches to this problem...

Towards Automated Analysis of Minirhizotron Images (2005)

Brian Fulkerson, Stefano Soatto, William Swenson, Mike Allen, Michael Hamilton

The ability to do robust, meaningful research with minirhizotron images is currently limited by the amount of time that can be spent by a human expert classifying the data. This poster focuses on...

Towards Automated Analysis of Minirhizotron Images (2005)

Brian Fulkerson, Stefano Soatto, William Swenson, Mike Allen, Michael Hamilton

The ability to do robust, meaningful research with minirhizotron images is currently limited by the amount of time that can be spent by a human expert classifying the data. This poster focuses on...

Learning Riemannian Metrics for Classification of Dynamical Models (2005)

Fabio Cuzzolin, Stefano Soatto

Consider the problem of classifying motions, encoded as dynamical models of a certain class. Standard nearest neighbor classification then reduces to find a suitable distance function in the space of...

ii (2005)

Yan Yu, Greg Pottie, Stefano Soatto, Songwu Lu, Ramesh Govindan, Deborah L. Estrin, ...

by

Multi-view stereo reconstruction of dense shape and complex appearance (2005)

A geometric approach to shape from defocus (2005)

appearance models.

Cluster Sampling and its Applications to Segmentation, Stereo and Motion (2005)

Abstract—We introduce a novel approach to shape from defocus, i.e., the problem of inferring the three-dimensional (3D) geometry of a scene from a collection of defocused images. Typically, in...

A.G. Barbu, Adrian Gheorghe Barbu, Adnan Darwiche, Stefano Soatto, Alan L. Yuille

of the Dissertation Cluster Sampling and its Applications to Segmentation, Stereo and Motion by University of California, Los Angeles, 2005 Professor Song-Chun Zhu, Chair Many computer vision...

KALMANSAC: Robust filtering by consensus (2005)

Dynamic shape and appearance modeling via moving and deforming layers (2005)

We propose an algorithm to perform causal inference of the state of a dynamical model when the measurements are corrupted by outliers. While the optimal (maximumlikelihood) solution has doubly...

Jeremy D. Jackson, Anthony Yezzi, Stefano Soatto

Abstract. We propose a model of the shape, motion and appearance of a sequence of images that captures occlusions, scene deformations, arbitrary viewpoint variations and changes in irradiance. This...

Motion competition: a variational approach to piecewise parametric motion segmentation (2005)

Active-Vision Control Systems For Complex Adversarial 3-D Environments,” A tutorial, IEEE american control conference (2005)

Abstract. We present a novel variational approach for segmenting the image plane into a set of regions of parametric motion on the basis of two consecutive frames from an image sequence. Our model is...

Eric N. Johnson, Anthony J. Calise, Allen R. Tannenbaum, Stefano Soatto, Naira Hovakimyan, Anthony J. Yezzi

Abstract — This tutorial session covers recent developments in methods that utilize 2-D and 3-D imagery (e.g., from LADAR, visual, FLIR, acoustic-location) to enable aerial vehicles to autonomously...

ii (2005)

Lewis David Girod, Stefano Soatto, Gregory J. Pottie, Miodrag Potkonjak

by

Fast marching method for generic shape from shading (2005)

Emmanuel Prados, Stefano Soatto

Abstract. We develop a fast numerical method to approximate the solutions of a wide class of equations associated to the Shape From Shading problem. Our method, which is based on the control theory...

Features for recognition: viewpoint invariance for non-planar scenes (2005)

Motion competition: a variational approach to piecewise parametric motion segmentation (2005)

Most current local feature detectors/descriptors implicitly assume that the scene is (locally) planar, an assumption that is violated at surface discontinuities. We show that this restriction is, at...

Daniel Cremers, Stefano Soatto

Abstract. We present a novel variational approach for segmenting the image plane into a set of regions of parametric motion on the basis of two consecutive frames from an image sequence. Our model is...

Autonomous Ground Vehicle in the DARPA Grand Challenge 1. OVERVIEW (2005)

Richard Mason, Jim Radford, Deepak Kumar, Robert Walters, Brian Fulkerson, Eagle Jones, ...

behind the development of Golem 2, the race vehicle. The subsystems devoted to obstacle detection, avoidance, and state estimation are discussed in more detail. An overview of vehicle performance in...

Multi-view stereo reconstruction of dense shape and complex appearance (2005)

A geometric approach to shape from defocus (2005)

We address the problem of estimating the three-dimensional shape and complex appearance of a scene from a calibrated set of views under fixed illumination. Our approach relies on a rank condition...

Layered active appearance models (2005)

Abstract—We introduce a novel approach to shape from defocus, i.e., the problem of inferring the three-dimensional (3D) geometry of a scene from a collection of defocused images. Typically, in...

Eagle Jones, Stefano Soatto

Active appearance models (AAMs) provide a framework for modeling the joint shape and texture of an image. An AAM is a compact representation of both factors in a conditionally linear model. However,...

Modeling dynamic scenes with active appearance (2005)

Fast Marching Method for Generic Shape From Shading (2005)

In this work we propose a model for video scenes that contain temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of active appearance...

Fast Marching Method for Generic Shape From Shading (2005)

We develop a fast numerical method to approximate the solutions of a wide class of equations associated to the Shape From Shading problem. Our method, which is based on the control theory and the...

Multiple View Feature Descriptors From Image Sequences Via Kernel Principal Component Analysis (2004)

We develop a fast numerical method to approximate the solutions of a wide class of equations associated to the Shape From Shading problem. Our method, which is based on the control theory and the...

Meltzer, Jason, Gupta, Rakesh, Soatto, Stefano, Yang, M H

We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the relative simplicity of small...

Modeling and Synthesis of Facial Motion Driven by Speech (2004)

Saison, Payam, Bissacco, A, Chiuso, A, Soatto, Stefano

We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a number of salient...

Integral invariant signatures (2004)

Manay, S, Hong, B W, Yezzi, A J, Soatto, Stefano

For shapes represented as closed planar contours, we introduce a class of functionals that are invariant with respect to the Euclidean and similarity group, obtained by performing integral...

Modeling and synthesis of facial motion driven by speech (2004)

Saisan, P, Bissacco, A, Chiuso, A, Soatto, Stefano

We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a number of salient...

Multiple view feature descriptors from image sequences via kernel principal component analysis (2004)

Meltzer, J, Yang, M H, Gupta, R, Soatto, Stefano

We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the relative simplicity of small...

Region-based segmentation on evolving surfaces with application to 3D reconstruction of shape and piecewise constant radiance (2004)

Jin, H L, Yezzi, A J, Soatto, Stefano

We consider the problem of estimating the shape and radiance of a scene from a calibrated set of images under the assumption that the scene is Lambertian and its radiance is piecewise constant. We...

Scene and motion reconstruction from defocused and motion-blurred images via anisotropic diffusion (2004)

Favaro, P, Burger, M, Soatto, Stefano

We propose a solution to the problem of inferring the depth map, radiance and motion of a scene from a collection of motion-blurred and defocused images. We model motion-blur and defocus as an...

Spatially homogeneous dynamic textures (2004)

Doretto, G, Jones, E, Soatto, Stefano

We address the problem of modeling the spatial and temporal second-order statistics of video sequences that exhibit both spatial and temporal regularity, intended in a statistical sense. We model...

Fast Visual Feature Selection and Tracking in a Hybrid Reconfigurable Architecture (2004)

Alessandro Bissacco, Jason Meltzer, Soheil Ghiasi, Stefano Soatto

We present a fast visual feature tracking system which takes advantage of dedicated hardware to perform the computationally intensive step of selection. A software system uses the output of the...

Visual Localization and Mapping with Multiple View Features (2004)

Jason Meltzer, Rakesh Gupta, Ming-Hsuan Yang, Stefano Soatto, UCLA Vision Lab

We propose a vision-based SLAM algorithm incorporating feature descriptors derived from multiple views of a scene, incorporating illumination and viewpoint variations. These descriptors are extracted...

Modeling and synthesis of facial motion driven by speech (2004)

Payam Saisan, Ro Bissacco, Ro Chiuso, Stefano Soatto

Abstract. We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a number of...

Integral invariant signatures (2004)

Siddharth Manay, Byung-woo Hong, Anthony J. Yezzi, Stefano Soatto

Abstract. For shapes represented as closed planar contours, we introduce a class of functionals that are invariant with respect to the Euclidean and similarity group, obtained by performing integral...

Kernel Density Estimation and Intrinsic Alignment for Knowledge-driven Segmentation: Teaching Level Sets to Walk (2004)

René Vidal, Yi Ma, Stefano Soatto, Shankar Sastry

Abstract. We present a geometric approach to 3-D motion estimation and segmentation of dynamic scenes containing multiple rigidly moving objects seen in two perspective views. We cast the problem in...

Daniel Cremers, Stanley J. Osher, Stefano Soatto

We address the problem of image segmentation with statistical shape priors in the context of the level set framework. Our paper makes two contributions: Firstly, we propose to generate invariance of...

Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion (2004)

Paolo Favaro, Martin Burger, Stefano Soatto

We propose a solution to the problem of inferring the depth map, radiance and motion field of a scene from a collection of motion-blurred and defocused images. We model motion-blurred and defocused...

Shedding light on stereoscopic segmentation (2004)

Daniel Cremers, Anthony J. Yezzi, Stefano Soatto

We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can...

Kernel density estimation and intrinsic alignment for knowledge-driven segmentation: Teaching level sets to walk (2004)

Daniel Cremers, Stanley J. Osher, Stefano Soatto

Abstract. We address the problem of image segmentation with statistical shape priors in the context of the level set framework. Our paper makes two contributions: Firstly, we propose a novel...

Tracking deformable moving objects under severe occlusions (2004)

Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatto

Abstract — We propose a nonlinear model for tracking a slowly deforming and moving contour despite significant occlusions. The contour is represented implicitly, and its motion is described by the...

Spatially homogeneous dynamic textures (2004)

Gianfranco Doretto, Eagle Jones, Stefano Soatto

Abstract. We address the problem of modeling the spatial and temporal second-order statistics of video sequences that exhibit both spatial and temporal regularity, intended in a statistical sense. We...

Integral invariant signatures (2004)

Siddharth Manay, Byung-woo Hong, Anthony J. Yezzi, Stefano Soatto

Abstract. For shapes represented as closed planar contours, we introduce a class of functionals that are invariant with respect to the Euclidean and similarity group, obtained by performing integral...

Kernel density estimation and intrinsic alignment for knowledge-driven segmentation: Teaching level sets to walk (2004)

René Vidal, Yi Ma, Stefano Soatto

Abstract. We present an algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views. Our...

Daniel Cremers, Stanley J. Osher, Stefano Soatto

Abstract. In this paper, we make two contributions to the field of level set based image segmentation. Firstly, we propose shape dissimilarity measures on the space of level set functions which are...

Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis (2004)

Jason Meltzer, Ming-hsuan Yang, Rakesh Gupta, Stefano Soatto

Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the relative simplicity...

A Variational Approach to Problems in Calibration of Multiple Cameras (2004)

Gozde Unal, Anthony Yezzi, Stefano Soatto, Greg Slabaugh

Abstract—This paper addresses the problem of calibrating camera parameters using variational methods. One problem addressed is the severe lens distortion in low-cost cameras. For many computer...

Region-based segmentation on evolving surfaces with application to 3D reconstruction of shape and piecewise constant radiance (2004)

Hailin Jin, Anthony J. Yezzi, Stefano Soatto

Abstract. We consider the problem of estimating the shape and radiance of a scene from a calibrated set of images under the assumption that the scene is Lambertian and its radiance is piecewise...

Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis (2004)

René Vidal, Yi Ma, Stefano Soatto

Abstract. We present an algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views. Our...

Jason Meltzer, Stefano Soatto, Ming-hsuan Yang, Rakesh Gupta

Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the relative simplicity...

Scene and motion reconstruction from defocused and motion-blurred images via anisotropic diffusion (2004)

Paolo Favaro, Martin Burger, Stefano Soatto

Abstract. We propose a solution to the problem of inferring the depth map, radiance and motion of a scene from a collection of motion-blurred and defocused images. We model motion-blur and defocus as...

A variational approach to scene reconstruction and image segmentation from motion-blur cues (2004)

Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis (2004)

In this paper we are interested in the joint reconstruction of geometry and photometry of scenes with multiple moving objects from a collection of motion-blurred images. We make simplifying...

Jason Meltzer, Ming-hsuan Yang, Rakesh Gupta, Stefano Soatto

Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the relative simplicity...

Towards Plenoptic Dynamic Textures (2003)

René Vidal, Yi Ma, Stefano Soatto, Shankar Sastry

Abstract. We present an algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views. Our...

Doretto, Gianfranco, Soatto, Stefano

We present a technique to infer a model of the spatio-temporal statistics of a collection of images of dynamic scenes seen from a moving camera. We use a time-variant linear dynamical system to...

Vision Based Navigation (2003)

Jason Meltzer, Stefano Soatto

We present a method for inferring the location of a robot relative to a three-dimensional map of its environment. The map, created off-line, consists of image patches, their locations in space, and...

An algebraic geometric approach to the identification of a class of linear hybrid systems (2003)

René Vidal, Stefano Soatto, Yi Ma, Shankar Sastry

We propose an algebraic geometric solution to the identification of a class of linear hybrid systems. We show that the identification of the model parameters can be decoupled from the inference of...

Deformotion: Deforming motion, shape average and the joint registration and approximation of structures in images (2003)

Stefano Soatto, Anthony J. Yezzi

What does it mean for a deforming object to be “moving ” (see Fig. 1)? How can we separate the overall motion (a finite-dimensional group action) from the more general deformation (a...

A semi-direct approach to structure (2003)

Hailin Jin, Stefano Soatto

from motion

Estimation of 3d surface shape and smooth radiance from 2d images: A level set approach (2003)

Hailin Jin, Anthony J. Yezzi, Yen-hsi Tsai, Li-tien Cheng, Stefano Soatto

We cast the problem of shape reconstruction of a scene as the global region segmentation of a collection of calibrated images. We assume that the scene is composed of a number of smooth surfaces and...

Multi-view stereo beyond lambert (2003)

Observability of linear hybrid systems (2003)

We consider the problem of estimating the shape and radiance of an object from a calibrated set of views under the assumption that the reflectance of the object is nonLambertian. Unlike traditional...

René Vidal, Ro Chiuso, Stefano Soatto, Shankar Sastry

Abstract. We analyze the observability of the continuous and discrete states of continuous-time linear hybrid systems. For the class of jumplinear systems, we derive necessary and sufficient...

Observability of linear hybrid systems (2003)

René Vidal, Ro Chiuso, Stefano Soatto, Shankar Sastry

Abstract. We analyze the observability of the continuous and discrete states of a class of continuous-time linear hybrid systems. We derive necessary and sufficient conditions that the structural...

A semi-direct approach to structure from motion (2003)

Multi-view stereo beyond lambert (2003)

The problem of structure from motion is often decomposed into two steps: feature correspondence and three-dimensional reconstruction. This separation often causes gross errors when establishing...

Dynamic Texture Segmentation (2003)

We consider the problem of estimating the shape and radiance of an object from a calibrated set of views under the assumption that the reflectance of the object is non-Lambertian. Unlike traditional...

Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto

We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics...

Dynamic texture segmentation (2003)

Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto

We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics...

Multi-view stereo beyond lambert (2003)

Modeling human gaits with subtleties (2003)

We consider the problem of estimating the shape and radiance of an object from a calibrated set of views under the assumption that the reflectance of the object is non-Lambertian. Unlike traditional...

Dynamic Texture Segmentation (2003)

Abstract: We present a novel approach to modeling subtleties in human motion. We represent the trajectories of a certain number of salient features on the human body as the output of a dynamical...

Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto

We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics...

References (2003)

Doretto, Gianfranco, Chiuso, Alessandro, Wu, Ying N, Soatto, Stefano

1 Brief summary of progress to date This project concerns the development of analytical and computational tools for the analysis of dynamic visual processes. In particular, emphasis has been given to...

Dynamic Textures (2002)

Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a novel...

Dynamic Textures (2002)

Doretto, Gianfranco, Chiuso, Alessandro, Wu, Ying N, Soatto, Stefano

Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a novel...

ii (2002)

Nirupama Bulusu, Mani B. Srivastava, Stefano Soatto, John Heidemann, Mario Gerla, Deborah L. Estrin, ...

by

Observability and identifiability of jump linear systems (2002)

René Vidal, Alessandro Chiuso, Stefano Soatto

We analyze the observability of the continuous and discrete states of a class of linear hybrid systems. We derive rank conditions that the structural parameters of the model must satisfy in order for...

A factorization method for 3D multi-body motion estimation and segmentation (2002)

René Vidal, Stefano Soatto, Shankar Sastry

We study the problem of estimating the motion of independently moving objects observed by a moving perspective camera. Given a set of image points and their optical flow in multiple frames, we show...

Learning shape from defocus (2002)

Region matching with missing parts (2002)

Abstract. We present a novel method for inferring three-dimensional shape from a collection of defocused images. It is based on the observation that defocused images are the null-space of certain...

Ro Duci, Anthony J. Yezzi, Sanjoy Mitter, Stefano Soatto, Scuola Normale Superiore

Abstract. We present a variational approach to the problem of registering planar shapes despite missing parts. Registration is achieved through the evolution of a partial differential equation that...

Two-view segmentation of dynamic scenes from the multibody fundamental matrix. TechniTwo-View Multibody Structure from Motion 25 cal Report, UCB/ERL M02/02 (2002)

René Vidal, Stefano Soatto, Shankar Sastry

We present a geometric approach to 3D motion segmentation of multiple moving objects seen in two perspective views. Our approach is based on the multibody epipolar constraint and its associated...

DOI: 10.1007/s11263-005-4839-7 Two-View Multibody Structure from Motion ∗ (2002)

René Vidal, Yi Ma, Stefano Soatto

Abstract. We present an algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views. Our...

Landmark based Inpainting from Multiple Views (2002)

Tony F. Chan, Stefano Soatto

Inpainting refers to the task of lling in missing or damaged regions of an image. Most existing inpainting algorithms are local in nature and extrapolate information from neighboring pixels into the...

Towards unsupervised detection of actions in clutter (2002)

Fabio Cuzzolin, Alessandro Bissacco, Ruggero Frezza, Stefano Soatto

We describe a characterization of "visual action " that encodes local photometry via a choice of interest operators and global dynamics via a realization of a stochastic dynamical...

A factorization method for 3D multi-body motion estimation and segmentation (2002)

René Vidal, Stefano Soatto, Shankar Sastry

We study the problem of estimating the motion of independently moving objects observed by a moving perspective camera. Given a set of image points and their optical flow in multiple frames, we show...

Structure from motion causally integrated over time (2002)

Ro Chiuso, Paolo Favaro, Student Member, Hailin Jin, Stefano Soatto

AbstractÐWe describe an algorithm for reconstructing three-dimensional structure and motion causally, in real time from monocular sequences of images. We prove that the algorithm is minimal and...

Deformotion - Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images (2002)

Stefano Soatto, Anthony J. Yezzi

What does it mean for a deforming object to be "moving"? How can we separate the overall motion (a finite-dimensional group action) from the more general deformation (a di#eomorphism)? In...

Structure from motion causally integrated over time (2002)

Ro Chiuso, Paolo Favaro, Student Member, Hailin Jin, Stefano Soatto

AbstractÐWe describe an algorithm for reconstructing three-dimensional structure and motion causally, in real time from monocular sequences of images. We prove that the algorithm is minimal and...

Inpainting from Multiple Views (2002)

Sung Ha Kang, Tony F. Chan, Stefano Soatto

Inpainting refers to the task of filling in missing or damaged regions of an image. In this paper, we are interested in the inpainting problem where the missing regions are so large that local...

Variational multiframe stereo in the presence of specular reflections (2002)

Hailin Jin, Anthony J. Yezzi, Stefano Soatto

We consider the problem of estimating the surface of an object from a calibrated set of views under the assumption that the reflectance of the object is non-Lambertian. In particular, we consider the...

c ○ 2003 Kluwer Academic Publishers. Manufactured in The Netherlands. Dynamic Textures (2001)

Gianfranco Doretto, Alessandro Chiuso, Ying Nian Wu, Stefano Soatto

Abstract. Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a...

c ○ 2003 Kluwer Academic Publishers. Manufactured in The Netherlands. Stereoscopic Segmentation (2001)

Anthony Yezzi, Stefano Soatto

Abstract. We cast the problem of multiframe stereo reconstruction of a smooth surface as the global region segmentation of a collection of images of the scene. Dually, the problem of segmenting...

Stereoscopic segmentation (2001)

Anthony J. Yezzi, Stefano Soatto

We cast the problem of multiframe stereo reconstruction of a smooth shape as the global region segmentation of a collection of images of the scene. Dually, the problem of segmenting multiple...

Dynamic textures (2001)

Stefano Soatto, Gianfranco Doretto, Ying Nian Wu

Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind but also talking faces, traffic...

Real-time feature tracking and outlier rejection with changes in illumination (2001)

Dynamic data factorization (2001)

We develop an efficient algorithm to track point features supported by image patches undergoing affine deformations and changes in illumination. The algorithm is based on a combined model of geometry...

Stefano Soatto, Alessandro Chiuso

minimum description length, image sequence compression, video coding,

Real-time feature tracking and outlier rejection with changes in illumination (2001)

Doretto, Gianfranco, Pundir, Prabhakar, Wu, Ying N, Soatto, Stefano

We develop an efficient algorithm to track point features supported by image patches undergoing affine deformations and changes in illumination. The algorithm is based on a combined model of geometry...

Dynamic Textures (2000)

Dynamic textures are sequences of images of moving scenes that exhibit certain stationariety properties in space and time; these include sea-waves, smoke, foliage, whirlwinds etc. We present a novel...

Real-time 3-d motion and structure of point features: Front-end system for vision-based control and interaction (2000)

mfm": 3-d motion from 2-d motion causally integrated over time (2000)

We present a system that consists of one camera connected to a Personal Computer that can (a) select and track a number of high-contrast point features on a sequence of images, (b) estimate their...

Alessandro Chiuso, Stefano Soatto

We introduce a provably minimal and stable nonlinear lter for causally estimating the three-dimensional motion of a scene in real time from a sequence of two-dimensional images. This problem is...

A Geometric Approach to Blind Deconvolution with Application to Shape from Defocus (2000)

Stefano Soatto, Paolo Favaro

We propose a solution to the generic \bilinear calibrationestimation problem" when using a quadratic cost function and restricting to (locally) translation-invariant imaging models. We apply the...

Shape and Radiance Estimation From the Information-divergence of Blurred Images (2000)

MFm: 3-D Motion From 2-D Motion Causally Integrated Over Time - Part II: Implementation (2000)

We formulate the problem of reconstructing the three-dimensional shape and radiance of a scene as the minimization of the Information-divergence between blurred images, and propose an algorithm that...

Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto

The causal estimation of three-dimensional motion from a sequence of two-dimensional images can be posed as a nonlinear filtering problem. In this paper we present a real-time implementation of an...

Stereoscopic Shading - Integrating Shape Cues in a Variational Framework (2000)

Hailin Jin, Anthony Yezzi, Stefano Soatto

We address the problem of integrating shading and multi-frame stereo cues within the framework of optimization in the innite-dimensional space of piecewise smooth surfaces. Cue integration then...

3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation (2000)

Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto

The causal estimation of three-dimensional motion from a sequence of two-dimensional images can be posed as a nonlinear filtering problem. We describe the implementation of an algorithm whose uniform...

Real-time 3-D Motion and Structure of Point Features: a Front-end System for Vision-based Control and Interaction (2000)

Monte Carlo Filtering on Lie Groups (2000)

We present a system that consists of one camera connected to a Personal Computer that can (a) select and track a number of high-contrast point features on a sequence of images, (b) estimate their...

Alessandro Chiuso, Stefano Soatto

We propose a nonlinear lter for estimating the trajectory of a random walk on a matrix Lie group with constant computational complexity. It is based on a nitedimensional approximation of the...

Optimal Structure From Motion: Local Ambiguities and Global Estimates (2000)

Alessandro Chiuso, Roger Brockett, Stefano Soatto

"Structure From Motion" (SFM) refers to the problem of estimating spatial properties of a three-dimensional scene from the motion of its projection onto a two-dimensional surface, such as...

Shape and radiance estimation from the information divergence of blurred images (2000)

3-d motion and structure from 2-d motion causally integrated over time: Implementation (2000)

Abstract. We formulate the problem of reconstructing the shape and radiance of a scene as the minimization of the information divergence between blurred images, and propose an algorithm that is...

Ro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto

Abstract. The causal estimation of three-dimensional motion from a sequence of two-dimensional images can be posed as a nonlinear filtering problem. We describe the implementation of an algorithm...

Euclidean Reconstruction and Reprojection up to Subgroups (1999)

Euclidean Reconstruction and Reprojection Up to Subgroups (1999)

The necessary and sufficient conditions for being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satisfied in practice. What exactly can be...

Yi Ma, Stefano Soatto, Jana Kosecka, Shankar Sastry

The necessary and sufficient conditions for being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satisfied in practice. What exactly can be...

Euclidean Reconstruction and Reprojection Up to Subgroups (1999)

Yi Ma Stefano, Yi Ma, Stefano Soatto, Jana Kosecka, Shankar Sastry

The necessary and sufficient conditionsfor being able to estimate scene structure, motionand camera calibration from a sequence of images are very rarely satisfied in practice. What exactly can be...

Euclidean Reconstruction and Reprojection Up to Subgroups (1999)

Yi Ma, Stefano Soatto, Jana Kosecká, Shankar Sastry

The necessary and sufficient conditions for being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satisfied in practice. What exactly, then,...

Euclidean Reconstruction and Reprojection up to Subgroups (1999)

Vision for Control: Optimality and Usability (1998)

The necessary and sufficient conditionsfor being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satisfied in practice. What exactly can be...

Reducing “Structure from Motion”: a general framework for dynamic vision. 2. Implementation and experimental assessment (1998)

This final report for the grant DAADl9-99-l-0139 and the associated instrumentation grant DURlP 4425l0-2l338 describes research conducted both at Washington University in St. Louis and at the...

Reducing “Structure from Motion”: a general framework for dynamic vision. 1. Modeling (1998)

For pt.1 see ibid., p.933-42 (1998). A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Despite...

Reducing "Structure From Motion": a General Framework for Dynamic Vision -- Part 2: Experimental Evaluation (1998)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of apparently unrelated models and estimation techniques. We propose a framework...

Reducing "structure from motion" 1: modeling. submitted to the (1998)

A number of methods have been proposed in the literature for estimating scenestructure and ego-motion from a sequence of images using dynamical models. Despite the fact that all methods may be...

Reducing "Structure From Motion": a General Framework for Dynamic Vision Part 1: Modeling (1998)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of different models and estimation techniques. We propose a framework that...

Optimal Structure From Motion: Local Ambiguities and Global Estimates (1998)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of apparently unrelated models and estimation techniques. We propose a framework...

Stefano Soatto, Roger Brockett

"Structure From Motion" (SFM) refers to the problem of estimating three-dimensional information about the environment from the motion of its two-dimensional projection onto a surface (for...

Reducing "Structure From Motion": a General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment (1998)

A Lagrangian Formulation of Nonholonomic Path Following (1998)

A number of methods have been proposed in the literature for estimating scenestructure and ego-motion from a sequence of images using dynamical models. Despite the fact that all methods may be...

Ruggero Frezza, Giorgio Picci, Stefano Soatto, Padova Italy

We address the problem of following an unknown planar contour with a nonholonomic vehicle based on visual feedback. The control task is to keep a point of the vehicle as close as possible to the...

Optimal Structure From Motion: Local Ambiguities and Global Estimates (1998)

Stefano Soatto, Roger Brockett

We present an analysis of SFM from the point of view of noise. This analysis results in an algorithm that is provably convergent and provably optimal with respect to a chosen norm. In particular, we...

Computer Vision. Euclidean Reconstruction and Reprojection Up to Subgroups (1998)

Reducing "structure from motion" 1: modeling. submitted to the (1998)

The necessary and sufficient conditions for being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satisfied in practice. What exactly can be...

Stefano Soatto, Stefano Soatto, Pietro Perona, Pietro Perona

A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Although all methods may be derived from a...

Reducing "structure from motion" 1: modeling. submitted to the (1998)

Stefano Soatto, Stefano Soatto, Pietro Perona, Pietro Perona

The literature on recursive estimation of structure and motion from monocular im-age sequences comprises a large number of different models and estimation techniques. We propose a framework that...

Optimal and Suboptimal Structure From Motion (1997)

Stefano Soatto, Roger Brockett

"Structure From Motion" (SFM) refers to the problem of estimating three-dimensional information about the environment from the motion of its two-dimensional projection onto a surface (for...

3-D Structure From Visual Motion: Modeling, Representation and Observability (1997)

A geometric framework for dynamic vision (1996)

The problem of "Structure From Motion" concerns the reconstruction of the three-dimensional structure of a scene from its projection onto a moving two-dimensional surface. Such a problem is...

Motion estimation via dynamic vision (1996)

This thesis explores the problem of inferring information about the three-dimensional world from its projections onto a camera (images). Among all visual cues, we do not address "pictorial" ones,...

Reducing "Structure From Motion": a General Framework for Dynamic Vision - Part 1: Modeling (1996)

Estimating the three-dimensional motion of an object from a sequence of projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation,...

Reducing "Structure From Motion": a General Framework for Dynamic Vision - Part 2: Experimental Evaluation (1996)

The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of different models and estimation techniques. We propose a framework that...

Depth from Brightness of Moving Images (1995)

A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Although all methods may be derived from a...

Motion from "X" by Compensating "Y" (1995)

In this note we describe a method for recursively estimating the depth of a scene from a sequence of images. The input to the estimator are brightness values at a number of locations of a grid in a...

Motion from Fixations (1995)

This paper analyzes the geometry of the visual motion estimation problem in relation to transformations of the input (images) that stabilize particular output functions such as the motion of a point,...

Motion from fixation (1995)

We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. The motivation comes...

Depth from Brightness of Moving Images (1995)

We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. The motivation comes...

Motion from "X " by Compensating CCY,, * (1995)

In this note we describe a method for recursively estimating the depth of a scene from a sequence of images. The input to the estimator are brightness values at a number of locations of a grid in a...

Stefano Soatto, Pietro Perona, Stefano Soatto, Pietro Perona

Motion from "X " by Compensating CCY,, * A unified framework for motion estimation from image sequences by compensating for the image-motion of a point, a line or a plane

On the Exact Linearization of Structure From Motion (1994)

Observability/Identifiability of Rigid Motion under Perspective Projection (1994)

The estimation of structure from motion has been a central task of computational vision over the last decade. As it is very well known, the problem is nonlinear due to the perspective nature of the...

Robust and Efficient Recovery of Rigid Motion from Subspace Constraints Solved using Recursive Identification of Nonlinear Implicit Systems (1994)

The "visual motion" problem consists of estimating the motion of an object viewed under projection. In this paper we address the feasibility of such a problem. We will show that the model which...

Dynamic Estimation of Rigid Motion from Perspective Views via Recursive Identification of Exterior Differential Systems with Parameters on a Topological Manifold (1994)

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion transformation and the perspective map. The time...

Recursive Estimation of Camera Motion from Uncalibrated Image Sequences (1994)

We formulate the problem of estimating the motion of a rigid object viewed under perspective projection as the identification of a dynamic model in Exterior Differential form with parameters on a...

Three Dimensional Transparent Structure Segmentation and Multiple 3D Motion Estimation from Monocular Perspective Image Sequences (1994)

In This memo we present an extension of the motion estimation scheme presented in a previous CDS technical report [14, 16], in order to deal with image sequences coming from an uncalibrated camera....

On the exact linearization of structure from motion (1994)

A three dimensional scene can be segmented using different cues, such as boundaries, texture, motion, discontinuities of the optical flow, stereo, models for structure etc. We investigate...

Observability/identifiability of rigid motion under perspective projection (1994)

The estimation of structure from motion has been a central task of computational vision over the last decade. As it is very well known, the problem is nonlinear due to the perspective nature of the...

Recursive Estimation Of Camera Motion From Uncalibrated Image Sequences (1994)

implicit systems, exterior differential systems, differential algebraic equations The "visual motion estimation " problem concerns the estimation of the motion of an object viewed...

Motion Estimation on the Essential Manifold (1994)

We describe a method for estimating the motion and structure of a scene from a sequence of images taken with a camera whose geometric calibration parameters are unknown. The scheme is based upon a...

Stefano Soatto, Ruggero Frezza, Pietro Perona

. We introduce a novel perspective for viewing the "ego-motion reconstruction" problem as the estimation of the state of a dynamical system having an implicit measurement constraint and...

Observability/Identifiability of Rigid Motion under Perspective Projection (1994)

Dynamic Visual Motion Estimation From Subspace Constraints (1994)

The "visual motion estimation" problem concerns the reconstruction of the motion of an object viewed under projection. This paper addresses the feasibility of such a problem when the object...

Three dimensional transparent structure segmentation and multiple 3D motion estimation from monocular perspective image sequences (1994)

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion constraint and the perspective map. The time derivative...

Observability/Identifiability of Rigid Motion under Perspective Projection (1994)

A three dimensional scene can be segmented using different cues, such as boundaries, texture, motion, discontinuities of the optical flow, stereo, models for structure etc. . We investigate...

Observability/Identifiability of Rigid Motion under Perspective Projection (1994)

The "visual motion" problem concerns the estimation of the motion of an object viewed under projection. This paper addresses the feasibility of such a problem. We will show that the model...

Motion Estimation via Dynamic Vision (1994)

The "visual motion estimation" problem concerns the reconstruction of the motion of an object viewed under projection. This paper addresses the feasibility of such a problem when the object...

Stefano Soatto, Pietro Perona, Ruggero Frezza, Giorgio Picci

Estimating the three dimensional motion of an object from a sequence of projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation,...

Motion Estimation via Dynamic Vision (1994)

Stefano Soatto, Ruggero Frezza, Pietro Perona

Estimating the three-dimensional motion of an object from a sequence of projections is of paramount importance in a variety of applications in control and robotics, such as autonomous navigation,...

Recursive estimation of camera motion from uncalibrated image sequences (1994)

Stefano Soatto, Ruggero Frezza, Pietro Perona, Stefano Soattot, Ruggero Frezzat, Pietro Peronatt

In This memo we present an extension of the motion estimation scheme presented in a previous CDS technical report [14, 161, in order to deal with image sequences coming from an uncalibrated camera....

Observability /IdentifiabiIity of Rigid Motion under Perspective Projection (1994)

Stefano Soatto, Pietro Perona, Stefano Soatto, Pietro Perona

exterior differential systems, differential algebraic equations The "visual motion " problem consists of estimating the motion of an object viewed under projection. In this paper we...

Dynamic estimation of rigid motion from perspective views via recursive identification of exterior differential systems with parameters on a topological manifold (1994)

Stefano Soatto, Ruggero Frezza, Pietro Perona, Stefano Soattot, Ruggero Frezzat, Pietro Peronaft, ...

We formulate the problem of estimating the motion of a rigid object viewed under perspective projection as the identification of a dynamic model in Exterior Differential form with parameters on a...

Recursive Motion Estimation on the Essential Manifold (1993)