Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms sy...
Segmentation has gained in popularity in stereo matching. However, it is not trivial to incorporate it in optical flow estimation due to the possible non-rigid motion problem. In t...
Abstract. The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework. Object models are formulated as generative models for range ...
Two challenges in computer vision are to accommodate noisy data and missing data. Many problems in computer vision, such as segmentation, filtering, stereo, reconstruction, inpain...
This paper presents a range image refinement technique for generating accurate 3D computer models of real objects. Range images obtained from a stereo-vision system typically expe...