用不确定性引导扩散桥，统一处理各类图像退化问题
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
- 将图像修复建模为由像素级不确定性驱动的随机传输过程
- 单次推理即可在多种退化下达到当前最优性能
- 适合需要统一修复多种图像质量问题的研究与应用
全功能图像修复（AiOIR）面临异构退化间冲突优化目标的根本挑战。现有方法常受限于粗粒度控制机制或固定映射调度，导致适应性不足。为此，我们提出不确定性感知扩散桥模型（UDBM），创新性地将AiOIR重构为由像素级不确定性引导的随机传输问题。通过引入松弛扩散桥形式，以宽松约束替代严格终端约束，既建模退化不确定性，又理论上解决了标准扩散桥中的漂移奇点问题。此外，设计双调制策略：噪声调度将多样退化对齐至共享高熵潜在空间，路径调度则基于熵正则化的黏性动力学自适应调节传输轨迹。通过有效修正传输几何与动力学，UDBM在单次推理中即实现多种修复任务的最先进性能。
原文摘要 · Abstract (English)
All-in-One Image Restoration (AiOIR) faces the fundamental challenge in reconciling conflicting optimization objectives across heterogeneous degradations. Existing methods are often constrained by coarse-grained control mechanisms or fixed mapping schedules, yielding suboptimal adaptation. To address this, we propose an Uncertainty-Aware Diffusion Bridge Model (UDBM), which innovatively reformulates AiOIR as a stochastic transport problem steered by pixel-wise uncertainty. By introducing a relaxed diffusion bridge formulation which replaces the strict terminal constraint with a relaxed constraint, we model the uncertainty of degradations while theoretically resolving the drift singularity inherent in standard diffusion bridges. Furthermore, we devise a dual modulation strategy: the noise schedule aligns diverse degradations into a shared high-entropy latent space, while the path schedule adaptively regulates the transport trajectory motivated by the viscous dynamics of entropy regularization. By effectively rectifying the transport geometry and dynamics, UDBM achieves state-of-the-art performance across diverse restoration tasks within a single inference step.
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。