Vision-Based 3D Reconstruction and Recognition
Related works
SOAP: Vision-Centric 3D Semantic Scene Completion with Scene-Adaptive Decoder and Occluded Region-Aware View Projection, CVPR, 2025, [project page]
BAAM: Monocular 3D pose and shape reconstruction with bi-contextual attention module and attention-guided modeling, CVPR, 2023, [paper] [project page]