通过双采样轨迹引入对称性信息，提升扩散模型图像修复效果
Equivariant Sampling for Improving Diffusion Model-based Image Restoration
- 设计双采样轨迹引入对称性约束，增强生成一致性
- 提出时间步感知调度策略，提升采样确定性与效率
- 无需增加计算成本，兼容现有方法且显著提升性能
近年来，生成模型尤其是扩散模型在图像修复（IR）任务中取得了显著进展。然而，现有的无问题特定性扩散模型图像修复（DMIR）方法难以充分利用扩散先验，导致性能受限。本文通过分析其采样过程，提出 EquS 方法，通过双重采样轨迹引入等变信息以改善生成质量。为进一步提升性能，提出时间步感知调度（TAS），优先处理确定性步骤以增强采样确定性与效率，形成 EquS$^+$。大量实验表明，该方法可兼容已有无问题特定性 DMIR 方法，在不增加计算开销的前提下显著提升修复性能。代码已公开于 https://github.com/FouierL/EquS。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。