AI RESEARCH
SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image
arXiv CS.CV
•
ArXi:2606.03994v1 Announce Type: new Reconstructing interactive, simulation-ready 3D scenes from a single image is a critical bottleneck for robotic manipulation. While recent single-image lifters recover plausible per-object shapes, composing them yields scenes that collapse under physical simulation due to interpenetrating, hovering, or sinking objects. Existing physics-aware methods address this strictly as a post-hoc layout correction, leaving the underlying geometric errors unresolved. To address this, we.