SOURCE-LINKED INTELLIGENCE

SpatialCrafter: Single Image World Modeling with Generative 3D Proxies

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

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. We present SpatialCrafter, a novel two-stage framework that addresses these issues by introducing a global 3D proxy for high-fidelity image-to-scene generation. Specifically, we decompose the generation process into global proxy generation and appearance re

Read original source ↗ Open in workspace

recordType

paper

region

Global