通过梯度管理提升扩散模型在图像修复中的稳定性与效果
Enhancing Diffusion Model Stability for Image Restoration via Gradient Management
- 提出渐进式似然预热与自适应方向动量，协同抑制梯度冲突和波动
- 在多种修复任务上实现更稳定生成，定量指标与视觉效果均达领先水平
- 适合关注图像修复中生成稳定性与扩散模型优化的研究者
扩散模型在图像修复中展现出巨大潜力，依赖强大的先验知识。现有方法通常将修复问题置于贝叶斯推断框架下，迭代执行去噪与似然引导步骤。然而，生成过程中这两部分的交互机制尚未充分研究。本文分析了其背后的梯度动态，发现先验与似然梯度方向存在显著冲突，且似然梯度随时间波动剧烈。这些不稳定性会破坏生成过程，降低修复性能。为此，提出稳定渐进梯度扩散（SPGD）方法，包含两项协同机制：(1) 渐进式似然预热策略，缓解梯度冲突；(2) 自适应方向动量（ADM）平滑，降低似然梯度波动。大量实验表明，SPGD 显著提升了生成稳定性，在多项定量指标上达到当前最优，并呈现更优视觉效果。代码已开源。
原文摘要 · Abstract (English)
Diffusion models have shown remarkable promise for image restoration by leveraging powerful priors. Prominent methods typically frame the restoration problem within a Bayesian inference framework, which iteratively combines a denoising step with a likelihood guidance step. However, the interactions between these two components in the generation process remain underexplored. In this paper, we analyze the underlying gradient dynamics of these components and identify significant instabilities. Specifically, we demonstrate conflicts between the prior and likelihood gradient directions, alongside temporal fluctuations in the likelihood gradient itself. We show that these instabilities disrupt the generative process and compromise restoration performance. To address these issues, we propose Stabilized Progressive Gradient Diffusion (SPGD), a novel gradient management technique. SPGD integrates two synergistic components: (1) a progressive likelihood warm-up strategy to mitigate gradient conflicts; and (2) adaptive directional momentum (ADM) smoothing to reduce fluctuations in the likelihood gradient. Extensive experiments across diverse restoration tasks demonstrate that SPGD significantly enhances generation stability, leading to state-of-the-art performance in quantitative metrics and visually superior results. Code is available at https://github.com/74587887/SPGD.
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。