Skip to yearly menu bar Skip to main content


Poster

Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks

Yuhao Liu · Zhanghan Ke · Fang Liu · Nanxuan Zhao · Rynson W.H. Lau

Arch 4A-E Poster #389
[ ] [ Paper PDF ]
Wed 19 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However, due to the randomness in the diffusion process, they often struggle with handling diverse low-level tasks that require details preservation. To overcome this limitation, we present a new Diff-Plugin framework to enable a single pre-trained diffusion model to generate high-fidelity results across a variety of low-level tasks. Specifically, we first propose a lightweight Task-Plugin module with a dual branch design to provide task-specific priors, guiding the diffusion process in preserving image content.We then propose a Plugin-Selector that can automatically select different Task-Plugins based on the text instruction, allowing users to edit images by indicating multiple low-level tasks with natural language.We conduct extensive experiments on 8 low-level vision tasks. The results demonstrate the superiority of Diff-Plugin over existing methods, particularly in real-world scenarios. Our ablations further validate that Diff-Plugin is stable, schedulable, and supports robust training across different dataset sizes.

Chat is not available.