AI RESEARCH
MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation
arXiv CS.CV
•
ArXi:2603.11633v1 Announce Type: new Recent unified 3D generation models have made remarkable progress in producing high-quality 3D assets from a single image. Notably, layout-aware approaches such as SAM3D can reconstruct multiple objects while preserving their spatial arrangement, opening the door to practical scene-level 3D generation. However, current methods are limited to single-view input and cannot leverage complementary multi-view observations, while independently estimated object poses often lead to physically implausible layouts such as interpenetration and floating artifacts.