| title | Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength |
|---|---|
| authors | Candi Zheng, Yuan Lan |
| date | 2026-09-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.00359 |
| affiliation | HKUST |
| upvotes | 5 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Diffusion models with prompt and reference image-guided editing have seen rapid progress, yet they remain too coarse for pixel-level control. One promising direction is to incorporate a soft mask that specifies spatially varying edit strengths but training such fine-grained control demands expensive pixel-wise annotations, while existing zero-shot methods often yield unsatisfactory results. We introduce SoftPaint, a new zero-shot sampling method that leverages soft masks to enable a continuous spectrum of edits, from fully preserving the original content to completely re-synthesizing the masked region. Going beyond zero-shot inpainting methods, we design a Langevin-iteration-based sampler that respects per-pixel soft mask strengths, which applies universally to image and video diffusion models, enabling tasks such as video editing. The method is gradient-free, memory-efficient, and achieves smooth, pixel-level edits across multiple image and video backbones. |
cite
@misc{zheng2026diffusion,
title={Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength},
author={Candi Zheng and Yuan Lan},
year={2026},
eprint={2610.00359},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.00359}
}