Stereo Matching With Color-Weighted Correlation, Hierarchical Belief Propagation And Occlusion Handling
This work addresses stereo vision for 3D reconstruction, but it appears incremental as it builds on existing energy minimization and belief propagation methods.
The paper tackles stereo matching by developing an algorithm that minimizes global energy using color-weighted correlation and hierarchical belief propagation, achieving top performance on the Middlebury datasets.
In this paper, we contrive a stereo matching algorithm with careful handling of disparity, discontinuity and occlusion. This algorithm works a worldwide matching stereo model which is based on minimization of energy. The global energy comprises two terms, firstly the data term and secondly the smoothness term. The data term is approximated by a color-weighted correlation, then refined in obstruct and low-texture areas in many applications of hierarchical loopy belief propagation algorithm. The results during the experiment are evaluated on the Middlebury data sets, showing that out algorithm is the top performer among all the algorithms listed there