A method to add Hidden Markov Models with application to learning articulated motion (2008)
Y. A. Hicks, P. M. Hall, A. D. Marshall
In this paper we present a method for adding Hidden Markov Models. The main advantages of our method are that it does not require the data the models had been trained on, allows a change in the...
Motion analysis in video: dolls, dynamic cues and Modern Art Abstract (2008)
E. Trucco, M. Chantler (editors, J. P. Collomosse, P. M. Hall
{jpc|pmh} @ cs.bath.ac.uk This paper addresses the problem of synthesising animations from video clips; in particular emphasising the motion of tracked objects. We introduce “dynamic cues ” as a...
J. P. Collomosse, Bath Ba Ay, P. M. Hall, Bath Ba Ay
We present a new non-photorealistic rendering (NPR) algorithm for rendering photographs in an impasto painterly style. We observe that most existing image-based NPR algorithms operate in a spatially...
Video Paintbox: The fine art of video painting (2008)
We present the Video Paintbox; a novel system capable of transforming video into stylised animations. Our system solves the problem of temporally coherent painting for a wide class of video, and is...
Structure Is a Visual Class Invariant (2008)
Xiao, B, Song, Yi Zhe, Balikai, Anupriya, Hall, P. M.
The problem of learning the class identity of visual objects has received considerable attention recently. With rare exception, all of the work to date assumes low variation in appearance, which...
J. P. Collomosse, D. Rowntree, P. M. Hall
The contribution of this paper is a novel non-photorealistic rendering (NPR) system capable of rendering motion within a video sequence in artistic styles. A variety of cartoon-style motion cues may...
RTcams: A new perspective on nonphotorealistic rendering from photographs (2007)
Hall, P. M., Collomosse, J. P., Song, Y. Z., Shen, P. Y., Li, C.
We introduce a simple but versatile camera model that we call the Rational Tensor Camera (RTcam). RTcams are well principled mathematically and provably subsume several important contemporary camera...
Salience-adaptive painterly rendering using genetic search (2006)
Collomosse, J. P., Hall, P. M.
We present a new non-photorealistic rendering (NPR) algorithm for rendering photographs in an impasto painterly style. We observe that most existing image-based NPR algorithms operate in a spatially...
Video motion analysis for the synthesis of dynamic cues and Futurist art (2006)
Collomosse, J. P., Hall, P. M.
This paper presents new methods for stylising video to produce cartoon motion emphasis cues and modern art. Specifically, we introduce "dynamic cues" as a class of motion emphasis cue, encompassing...
Stroke surfaces: Temporally coherent artistic animations from video (2005)
Collomosse, J. P., Rowntree, D., Hall, P. M.
The contribution of this paper is a novel framework for synthesizing nonphotorealistic animations from real video sequences. We demonstrate that, through automated mid-level analysis of the video...
Rendering cartoon-style motion cues in post-production video (2005)
Collomosse, J. P., Rowntree, D., Hall, P. M.
The contribution of this paper is a novel non-photorealistic rendering (NPR) system capable of rendering motion within a video sequence in artistic styles. A variety of cartoon-style motion cues may...
Genetic paint: A search for salient paintings (2005)
Collomosse, J. P., Hall, P. M.
The contribution of this paper is a novel non-photorealistic rendering (NPR) algorithm for rendering real images in an impasto painterly style. We argue that figurative artworks are salience maps,...
Video Paintbox: The fine art of video painting (2005)
Collomosse, J. P., Hall, P. M.
We present the Video Paintbox; a novel system capable of transforming video into stylised animations. Our system solves the problem of temporally coherent painting for a wide class of video, and is...
A Mid-level Description of Video, with Application to Non-photorealistic Animation (2004)
Collomosse, J. P., Hall, P. M.
The contribution of this paper is a novel spatiotemporal description of real video sequences. Our description comprises a set of surfaces that separate objects in the video, and an accompanying...
A Trainable Low-level Feature Detector (2004)
Hall, P. M., Owen, M.J, Collomosse, J. P.
We introduce a trainable system that simultaneously filters and classifies low-level features into types specified by the user. The system operates over full colour images, and outputs a vector at...
Video analysis for Cartoon-style Special Effects (2003)
Collomosse, J.P, Rowntree, D, Hall, P. M.
In recent years the Vision community has shown interest in processing images and video for use by the entertainment industries. Typical applicationsinclude 3D reconstruction of models, and rendering...
Cubist style rendering from photographs (2003)
Abstract--- The contribution of this paper is a novel nonphotorealistic rendering (NPR) technique, influenced by the style of Cubist art. Specifically we are motivated by artists such as Picasso and...
J. P. Collomosse, J. P. Collomosse, D. Rowntree, D. Rowntree, P. M. Hall, P. M. Hall
The contribution of this paper is a novel framework for the automated synthesis of non-photorealistic animations from video sequences. Our approach is unique in that we interpret the source video...
Video Analysis for Cartoon-like Special Effects (2003)
J. P. Collomosse, D. Rowntree, P. M. Hall
In recent years the Vision community has shown interest in processing images and video for use by the entertainment industries. Typical applications include 3D reconstruction of models, and rendering...
Cubist style rendering from photographs (2003)
Collomosse, J. P., Hall, P. M.
The contribution of this paper is a novel nonphotorealistic rendering (NPR) technique, influenced by the style of Cubist art. Specifically, we are motivated by artists such as Picasso and Braque, who...
Tracking people in three dimensions using a hierarchical model of dynamics (2002)
Karaulova, I. A., Hall, P.M., Marshall, A.D.
We propose a novel hierarchical model of human dynamics for view independent tracking of a human figure in monocular video sequences. The model is trained using real data from a collection of people....
Painterly Rendering using Image Salience (2002)
Collomosse, J. P., Hall, P. M.
The contribution of this paper is a novel nonphotorealistic rendering (NPR) technique, capable of producing an artificial ?hand-painted? effect on 2D images, such as photographs. Our method requires...
Painterly Rendering using Image Salience (2002)
Collomosse And Hall, J. P. Collomosse, P. M. Hall
The contribution of this paper is a novel nonphotorealistic rendering (NPR) technique, capable of producing an artificial `hand-painted' effect on 2D images, such as photographs. Our method...
A hierarchical model of dynamics for tracking people with a single video camera (2000)
I. A. Karaulova, P. M. Hall, A. D. Marshall
We propose a novel hierarchical model of human dynamics for view independent tracking of the human body in monocular video sequences. The model is trained using real data from a collection of people....
A hierarchical model of dynamics for tracking people with a single video camera (2000)
I. A. Karaulova, P. M. Hall, A. D. Marshall
We propose a novel hierarchical model of human dynamics for view independent tracking of the human body in monocular video sequences. The model is trained using real data from a collection of people....
The RAISE Language Group. The RAISE Specification Language. BCS Practitioner Series (1992)
Abstract. The contribution of this paper is a novel non-photorealistic rendering (NPR) algorithm for rendering real images in an impasto painterly style. We argue that figurative artworks are...
Stroke Surfaces: A Spatiotemporal Framework for Temporally Coherent Non-photorealistic Animations
This paper outlines a novel framework for the automated synthesis of non-photorealistic animations from video sequences. Our approach is unique among such animation techniques in that we process the...