AI RESEARCH
Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion
arXiv CS.CV
•
ArXi:2604.05780v1 Announce Type: new Monocular Semantic Scene Completion (SSC) aims to reconstruct complete 3D semantic scenes from a single RGB image, offering a cost-effective solution for autonomous driving and robotics. However, the inherently imbalanced nature of voxel distributions, where over 93% of voxels are empty and foreground classes are rare, poses significant challenges. Existing methods often suffer from redundant emphasis on uninformative voxels and poor generalization to long-tailed categories.