Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion

arXiv:2303.13959v4 Announce Type: replace
Abstract: 3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations. Previous camera-based methods struggle to predict accurate semantic scenes due to inherent geometric ambiguity and incomplete observations. In this paper, we resort to stereo matching technique and bird's-eye-view (BEV) representation learning to address such issues in SSC. Complementary to each other, stereo matching mitigates geometric ambiguity with epipolar constraint while BEV representation enhances the hallucination …

arxiv cs.cv geometry representation semantic type