AI RESEARCH
Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction
arXiv CS.CV
•
ArXi:2603.22852v1 Announce Type: new 3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a multi-modal framework that bypasses dense volumetric processing by modeling the scene as a compact collection of semantic 3D Gaussians. To ensure geometric completeness, we propose a LiDAR Completion Diffuser (LCD) that recovers missing structures from sparse LiDAR to initialize robust Gaussian anchors. Furthermore, we