AI RESEARCH
Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
arXiv CS.CV
•
ArXi:2605.21472v1 Announce Type: new View-conditioned 3D generators such as SAM 3D, TRELLIS and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual observation often arrives as long monocular streams. Naively applying these generators to each streaming frame independently leads to severe temporal inconsistency in the generated results. To address this problem, we propose Stream3D, the first