Digging Into Normal Incorporated Stereo Matching

arXiv:2402.18171v1 Announce Type: new
Abstract: Despite the remarkable progress facilitated by learning-based stereo-matching algorithms, disparity estimation in low-texture, occluded, and bordered regions still remains a bottleneck that limits the performance. To tackle these challenges, geometric guidance like plane information is necessary as it provides intuitive guidance about disparity consistency and affinity similarity. In this paper, we propose a normal incorporated joint learning framework consisting of two specific modules named non-local disparity propagation(NDP) and affinity-aware residual learning(ARL). The estimated normal map …

abstract algorithms arxiv challenges cs.cv guidance information low normal performance plane progress texture type