State-of-the-art stereo vision algorithms utilize color changes as important cues for object boundaries. Most methods impose heuristic restrictions or priors on disparities, for e...
In this paper we present a method of combining stereo and shape-from-shading information, taking account of the local reliability of each shape estimate. Local estimates of dispar...
Many vision problems have been formulated as en- ergy minimization problems and there have been signif- icant advances in energy minimization algorithms. The most widely-used energ...
Wonsik Kim (Seoul National University), Kyoung Mu ...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
Visual vocabulary serves as a fundamental component in many computer vision tasks, such as object recognition, visual search, and scene modeling. While state-of-the-art approaches...