SpatialCrafter：单图世界建模的生成式 3D 代理
Original title: SpatialCrafter: Single Image World Modeling with Generative 3D Proxies
ResearchAI 75
Source: arXiv cs.ROPublish time unverified
arXiv:2608.27073v2 Announce Type: replace-cross Abstract: Explorable image-to-scene generation is essential for applications in gaming, robotics, and virtual reality. Existing methods based on video diffusion model (VDM) commonly rely on incomplete conditioning signals such as sparse point clouds or 2D panoramas, leading to stochastic hallucinations, long-term drifts and suboptimal 3D consistency.