Skip to content

Author

Jing-Yi Pan

We have 1 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement

A Support Token Refinement strategy is proposed, which injects diffusion-generated support evidence as confidence-weighted auxiliary tokens to refine under-observed regions while preserving the original spatial anchor of reliable observations while preserving the original spatial anchor.

Jing-Yi Pan, Dan Xu, Qiong Luo · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.