Variable Baseline/Resolution Stereo (2009)
David Gallup, Jan-michael Frahm, Marc Pollefeys
We present a novel multi-baseline, multi-resolution stereo method, which varies the baseline and resolution proportionally to depth to obtain a reconstruction in which the depth error is constant....
Fast Gain-Adaptive KLT Tracking on the GPU (2009)
Christopher Zach, David Gallup, Jan-michael Frahm
High-performance feature tracking from video input is a valuable tool in many computer vision techniques and mixed reality applications. This work presents a refined and substantially accelerated...
Rahul Raguram, Jan-michael Frahm, Marc Pollefeys
Abstract. The Random Sample Consensus (RANSAC) algorithm is a popular tool for robust estimation problems in computer vision, primarily due to its ability to tolerate a tremendous fraction of...
Joint Feature Tracking and Radiometric Calibration from Auto-Exposure Video (2008)
Seon Joo Kim, Jan-michael Frahm, Marc Pollefeys
To capture the full brightness range of natural scenes, cameras automatically adjust the exposure value which causes the brightness of scene points to change from frame to frame. Given such a video...
Evaluation of Large Scale Scene Reconstruction (2008)
Paul Merrell, Jan-michael Frahm, Marc Pollefeys
We present an evaluation methodology and data for large scale video-based 3D reconstruction. We evaluate the effects of several parameters and draw conclusions that can be useful for practical...
Evaluation of Large Scale Scene Reconstruction (2008)
Paul Merrell, Jan-michael Frahm, Marc Pollefeys
We present an evaluation methodology and data for large scale video-based 3D reconstruction. We evaluate the effects of several parameters and draw conclusions that can be useful for practical...
Gregory Welch, Marc Pollefeys, Jan-michael Frahm
We introduce a novel approach to on-line structure from motion, using a pipelined pair of extended Kalman filters to improve accuracy with a minimal increase in computational cost. The two filters, a...
Calibration of a Surface Light Field Capture System (2008)
Jan-michael Frahm, Greg Coombe, Anselmo Lastra
In this paper we introduce a simple procedure to calibrate a surface light field capture system. This system was developed to capture the illumination from a virtual environment map [2]. However, the...
Differential Camera Tracking through Linearizing the Local Appearance Manifold (2008)
Hua Yang, Marc Pollefeys, Greg Welch, Jan-michael Frahm, Adrian Ilie
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspectives lie on a 6D...
Abstract Visual-Geometric Scene Reconstruction from Image Streams (2008)
Reinhard Koch, Jan-michael Frahm
Visual-geometric scene reconstructions capture the visual appearance and geometry of real 3D scenes from image streams. Depending on the type of camera motion and type of scene structure, either 2D...
Jan-michael Frahm, Reinhard Koch, Christian Albrechts
We address the problem of using external rotation information together with uncalibrated video sequences for improved calibration and 3Dreconstruction. It is shown that with a combination of a linear...
Differential Camera Tracking through Linearizing the Local Appearance Manifold (2008)
Hua Yang, Marc Pollefeys, Greg Welch, Jan-michael Frahm, Adrian Ilie
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspectives lie on a 6D...
Gregory Welch, Marc Pollefeys, Jan-michael Frahm
We introduce a novel approach to on-line structure from motion, using a pipelined pair of extended Kalman filters to improve accuracy with a minimal increase in computational cost. The two filters, a...
Differential Camera Tracking through Linearizing the Local Appearance Manifold (2008)
Hua Yang, Marc Pollefeys, Greg Welch, Jan-michael Frahm, Adrian Ilie
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspectives lie on a 6D...
Sudipta N. Sinha, Jan-michael Frahm, Marc Pollefeys, Yakup Genc
Abstract This paper describes novel implementations of the KLT feature track-ing and SIFT feature extraction algorithms that run on the graphics processing unit (GPU) and is suitable for video...
Fast Global Labeling for Real-Time Stereo Using Multiple Plane Sweeps (2008)
Christopher Zach, David Gallup, Jan-michael Frahm, Marc Niethammer
This work presents a real-time, data-parallel approach for global label assignment on regular grids. The labels are selected according to a Markov random field energy with a Potts prior term for...
Abstract Visual-Geometric Scene Reconstruction from Image Streams (2007)
Reinhard Koch, Jan-michael Frahm
Visual-geometric scene reconstructions capture the visual appearance and geometry of real 3D scenes from image streams. Depending on the type of camera motion and type of scene structure, either 2D...
Gain Adaptive Real-Time Stereo Streaming (2007)
Kim, Seon Joo, Gallup, D., Frahm, Jan-Michael, Akbarzadeh, A., Yang, Q., Yang, R., ...
This paper introduces a multi-view stereo matcher that generates depth in real-time from a monocular video stream of a static scene. A key feature of our processing pipeline is that it estimates...
Real-Time Visibility-Based Fusion of Depth Maps (2007)
Paul Merrell, Amir Akbarzadeh, Liang Wang, Jan-michael Frahm
We present a viewpoint-based approach for the quick fusion of multiple stereo depth maps. Our method selects depth estimates for each pixel that minimize violations of visibility constraints and thus...
Real-Time Visibility-Based Fusion of Depth Maps (2007)
Paul Merrell, Amir Akbarzadeh, Liang Wang, Jan-michael Frahm
We present a viewpoint-based approach for the quick fusion of multiple stereo depth maps. Our method selects depth estimates for each pixel that minimize violations of visibility constraints and thus...
Visual odometry for nonoverlapping views using second-order cone programming (2007)
Jae-hak Kim, Richard Hartley, Jan-michael Frahm, Marc Pollefeys
Abstract. We present a solution for motion estimation for a set of cameras which are firmly mounted on a head unit and do not have overlapping views in each image. This problem relates to ego-motion...
GPU-based Video Feature Tracking and Matching (2006)
Sudipta N. Sinha, Jan-michael Frahm, Marc Pollefeys, Yakup Genc
Abstract This paper describes novel implementations of the KLT feature tracking and SIFT feature extraction algorithms that run on the graphics processing unit (GPU) and is suitable for video...
GPU-based Video Feature Tracking and Matching (2006)
Sudipta N. Sinha, Jan-michael Frahm, Marc Pollefeys
Extraction and matching of salient feature points in video is important in many computer vision tasks like object detection, recognition and structure from motion. While certain sequential tasks like...
Ransac for (quasi-)degenerate data (qdegsac (2006)
Jan-michael Frahm, Marc Pollefeys
The computation of relations from a number of potential matches is a major task in computer vision. Often RANSAC is employed for the robust computation of relations such as the fundamental matrix....
Camera self-calibration with known camera orientation / (2005)
Zugl.: Kiel, University, Diss., 2005.
Markerless augmented reality with light source estimation for direct illumination (2005)
Jan-michael Frahm, Kevin Koeser, Daniel Grest, Reinhard Koch
We present a markerless augmented reality system with intuitive positioning and realistic direct lighting of virtual objects. Our approach exploits a two camera system consisting of a TV-camera and a...
Pose estimation for multi-camera systems (2004)
Jan-michael Frahm, Kevin Köser, Reinhard Koch
Abstract. We propose an approach for pose estimation based on a multi-camera system with known internal camera parameters. We only assume for the multi-camera system that the cameras of the system...
Robust camera calibration from images and rotation data (2003)
Jan-michael Frahm, Reinhard Koch
Abstract. The calibration of cameras from external orientation information and image processing is addressed in this paper. We will show that in the case of known rotation the calibration of rotating...
A color similarity measure for robust shadow removal in real time (2003)
Daniel Grest, Jan-michael Frahm, Reinhard Koch
We introduce an approach for realtime segmentation of a scene into foreground objects, background, and object shadows superimposed on the background. To segment foreground objects, we use an adaptive...
Distributed interaction processing and visualization of 3d scenes in realtime (2003)
Jan-michael Frahm, Reinhard Koch
A distributed realtime system for immersive visualization is presented which uses distributed interaction for control. We will focus on a network architecture for distributed interaction processing...
Camera calibration with known rotation (2003)
Jan-michael Frahm, Reinhard Koch
We address the problem of using external rotation information with uncalibrated video sequences. The main problem addressed is, what is the benefit of the orientation information for camera...
Network protocol for interaction and scalable distributed visualization (2002)
Jan-michael Frahm, Reinhard Koch
In the last decade the visualization of virtual environments and interaction within was possible only with specialized hardware. This hardware was very expensive, had a lack of scalability and used...
Distributed Realtime Interaction and Visualization System (2002)
Jan-Michael Frahm, Felix Woelk, Jan Woetzel, Reinhard Koch
A distributed realtime system for immersive visualization is presented which uses distributed interaction for control. We will focus on user tracking with fixed and pan-tilt-zoom cameras,...
Plenoptic Modeling of 3D Scenes with a Sensor-augmented Multi-Camera Rig (2002)
Reinhard Koch, Jan-Michael Frahm, Jan Woetzel
We propose a system for robust modeling and visualisation of complex outdoor scenes from multi-camera image sequences and additional sensor information. A camera rig with one or more fire-wire...