Gregor Miller

Learn More
This paper presents a novel volumetric reconstruction technique that combines shape-from-silhouette with stereo photo-consistency in a global optimisation that enforces feature constraints across multiple views. Human shape reconstruction is considered where extended regions of uniform appearance, complex self-occlusions and sparse feature cues represent a(More)
We have built a novel vision processing system architecture called Hive. Hive fills a gap in the vision middleware by providing mechanisms for simple setup and configuration of distributed vision computation. Hive facilitates communication between independent cross-platform modules via an extensible protocol, allowing these distributed modules to form a(More)
The visual hull is widely used to produce three dimensional models from multiple views, due to the reliability of the resulting surface. This paper presents a novel method for efficiently evaluating the exact view-dependent visual hull without using approximations. Methods for selecting intersections and ordering them via the cross ratio are presented.(More)
Recently there have been a number of proposals for the use of artificial evolution as a radically new approach to the development of control systems for autonomous robots. This paper explains the artificial evolution approach, using work at Sussex to illustrate it. The paper revolves around a case study on the concurrent evolution of control networks and(More)
This paper introduces a system that automatically classifies registration problems based on the type of registration required. Rather than rely on a single “best” algorithm, the proposed system is made up of a suite of image registration techniques. Image pairs are analyzed according to the types of variation that occur between them, and appropriate(More)
In this paper we introduce a video-based representation for free viewpoint visualization and motion control of 3D character models created from multiple view video sequences of real people. Previous approaches to video-based rendering provide no control of scene dynamics to manipulate, retarget, and create new 3D content from captured scenes. Here we(More)
This contribution introduces a new approach of using multi-camera images of an event to provide a free-viewpoint video visualisation of sport scenes. This allows a virtual camera to be moved freely around and to view the action from any angle. The system is based on 3D reconstruction techniques previously developed for studio use. A number of different 3D(More)
Target selection is a fundamental aspect of interaction and is particularly challenging when targets are moving. We address this problem by introducing a novel selection technique we call Hold which temporarily pauses the content while selection is in progress to provide a static target. By studying users, we evaluate our method against two others for(More)
We constructed a personal, spherical, multi-projector perspective-corrected rear-projected display called <i>Spheree.</i> Spheree uses multiple calibrated pico-projectors inside a spherical display with content rendered from a user-centric viewpoint. Spheree uses optical tracking for head-coupled rendering, providing parallax-based 3D depth cues. Spheree is(More)
We are addressing two aspects of vision-based system development that are not fully exploited in current frameworks: abstraction over low-level details and high-level module reusability. Through an evaluation of existing frameworks, we relate these shortcomings to the lack of systematic classification of sub-tasks in vision-based system development. In this(More)