Abstract--Real-time stereo vision is attractive in many applications like robot navigation and 3D scene reconstruction. Data parallel platforms, e.g. GPU, is often used for real-ti...
Wei Yu, Tsuhan Chen, Franz Franchetti, James C. Ho...
Every stereovision application must cope with the correspondence problem. The space of the matching variables, often consisting of spatial coordinates, intensity and disparity, is...
Markov random field models provide a robust and unified framework for early vision problems such as stereo, optical flow and image restoration. Inference algorithms based on graph...
Nearly all existing methods for stereo reconstruction assume that scene reflectance is Lambertian, and make use of color constancy as a matching invariant. We introduce a new inva...
This paper describes the design and implementation of an algorithm for improving the performance of stereo vision in environments presenting repetitive patterns or regions with re...