Equivariant Sampling for Improving Diffusion Model-based Image Restoration
This work addresses a specific bottleneck in image restoration for researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the suboptimal performance of problem-agnostic diffusion model-based image restoration methods by introducing EquS, which uses equivariant information and dual sampling trajectories, and EquS+ with a timestep-aware schedule, achieving significant performance boosts on benchmarks without added computational cost.
Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by analyzing their sampling process and providing effective solutions. We introduce EquS, a DMIR method that imposes equivariant information through dual sampling trajectories. To further boost EquS, we propose the Timestep-Aware Schedule (TAS) and introduce EquS$^+$. TAS prioritizes deterministic steps to enhance certainty and sampling efficiency. Extensive experiments on benchmarks demonstrate that our method is compatible with previous problem-agnostic DMIR methods and significantly boosts their performance without increasing computational costs. Our code is available at https://github.com/FouierL/EquS.