发表机构
Jiangsu University（江苏大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有DMIR方法忽略生成过程动态性的局限，提出LEADer框架，通过空间域逐像素不确定性调节与时间域自适应轨迹剪枝，提升图像复原性能并减少采样时间，且可即插即用集成至多种DMIR基线。
AI 中文摘要
扩散模型在图像复原任务中已展现出卓越的有效性。然而，现有的基于扩散模型的图像复原（DMIR）方法在引导图像重建时，通常依赖固定的数据约束和均匀步长，从而忽略了生成过程的动态性。这种刚性设计使模型易受空间非均匀退化的影响，进而导致结构失真和精细细节丢失。同时，均匀步长会引入计算冗余，而朴素的步长缩减策略往往会累积近似误差。为解决这些局限，我们提出了局部认知不确定性引导主动采样框架（LEADer）。在空间域中，LEADer利用逐像素不确定性动态调节零空间内的先验强度，有效平衡细节保留与伪影抑制；在时间域中，它通过不确定性迹量化采样稳定性，以实现自适应轨迹剪枝，从而加速收敛。理论证明表明，我们的框架可实现严格的数据一致性，且轨迹剪枝策略具有确定性误差界，可保证跳过采样下的稳定收敛。值得注意的是，我们的即插即用方法可无缝集成到多种DMIR基线中。大量实验表明，LEADer提升了多个最先进DMIR方法的性能，同时在内存开销可忽略的情况下显著减少了采样时间。代码可在指定的URL获取。
英文摘要
Diffusion models have demonstrated remarkable effectiveness in image restoration tasks. However, when guiding image reconstruction, existing Diffusion Model-based Image Restoration (DMIR) methods typically rely on fixed data constraints and uniform step sizes, thereby overlooking the dynamic nature of the generative process. Such rigid designs render the models vulnerable to spatially non-uniform degradations, thus resulting in structural distortions and loss of fine details. Meanwhile, uniform step sizes introduce computational redundancy, whereas naïve step reduction strategies tend to accumulate approximation errors. To address these limitations, we propose a Local Epistemic Uncertainty Guided Active Sampling framework (LEADer). In the spatial domain, LEADer leverages pixel-wise uncertainty to dynamically modulate the prior strength within the null space, which effectively balances detail preservation and artifact suppression. In the temporal domain, it quantifies sampling stability via the uncertainty trace to enable adaptive trajectory pruning, thereby accelerating convergence. Theoretical proofs demonstrate that our framework achieves strict data consistency, while the trajectory pruning strategy admits a deterministic error bound, thereby guaranteeing stable convergence under skip sampling. Notably, our plug-and-play method can be seamlessly integrated into various DMIR baselines. Extensive experiments show that LEADer improves the performance of multiple state-of-the-art DMIR methods, while significantly reducing sampling time with negligible memory overhead. Code is available at https://github.com/JiaqiZhang-Sengoku/LEADer.
Comments12 Pages, 7 Figures, 5 Tables. Accepted to ACM Multimedia 2026 Oral!
