Abstract: 2D-3D joint learning is essential and effective for fundamental 3D vision tasks, such as 3D semantic segmentation, due to the complementary information these two visual modalities contain.

Abstract: Recently, the pure camera-based Bird’s-Eye-View (BEV) perception provides a feasible solution for economical autonomous driving. However, the existing BEV-based multiview 3D detectors ...

This repository is the official implementation of "Diffusion²: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models". In this paper, we propose to achieve 4D ...