Bri3D: Bridging the Object-Scene Gap in Single-Image 3D Generation via Scene-Anchor

Bri3D is a new framework for generating compositional 3D scenes from a single image. It bridges scene-level structural reasoning with object-level generative priors by using instance-aware voxel scene anchors that encode coarse geometry and spatial arrangements. The method refines each anchor into a pose-preserving voxel support, allowing a frozen object generator to produce detailed, textured geometry while separating scene organization from object-scale detail synthesis, resulting in faster and higher-quality scene generation compared to prior works.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.