Preprint
Oct 2026
Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
3D scene inpainting aims to recover missing or occluded regions in edited 3D scenes, while ensuring geometric and textural consistency. Existing approaches, however, typically require accurately calibrated camera poses, which restricts their applicability in casual, in-the-wild scenarios and introduces additional prepr...
Jing-Yi Pan, Dan Xu, Qiong Luo
· 0 citations