Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
Researchers have developed Stream3D, a novel mechanism designed to enhance 3D generation from sequential visual data. This system allows existing view-conditioned 3D generators to process monocular streams without retraining by employing a dynamic evidential memory. This memory selectively caches informative frames, preventing temporal inconsistencies and managing memory footprint efficiently. AI
IMPACT Enables more consistent 3D reconstructions from continuous video feeds, potentially improving applications in robotics and augmented reality.