AI RESEARCH
Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image
arXiv CS.CV
•
ArXi:2603.05908v1 Announce Type: new Current compositional image-to-3D scene generation approaches construct 3D scenes by time-consuming iterative layout optimization or inflexible joint object-layout generation. Moreover, most methods rely on limited field-of-view perspective images, hindering the creation of complete 360-degree environments. To address these limitations, we design Pano3DComposer, an efficient feed-forward framework for panoramic images. To decouple object generation from layout estimation, we propose a plug-and-play Object-World Transformation Predictor.