提出DAPS++，让扩散模型修复图像更高效精准
DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
- 分离扩散初始化与测量一致性优化，直接由数据约束引导重建
- 减少函数求值次数和优化步骤，计算效率显著提升
- 揭示统一扩散轨迹为何有效，适合图像修复任务研究者
从贝叶斯视角看，基于得分的扩散模型通过联合推断解决逆问题，将似然与先验融合以指导采样。然而，这种形式无法解释其实际行为：先验提供的引导有限，重建主要依赖测量一致性项，导致推断过程实际上脱离了扩散动态。我们发现，这些求解器中的扩散先验主要作为热启动，将估计值置于数据流形附近，而重建几乎完全由测量一致性驱动。基于此观察，我们提出 extbf{DAPS++}，彻底解耦基于扩散的初始化与似然驱动的精炼，使似然项能更直接地引导推断，同时保持数值稳定性，并揭示为何统一的扩散轨迹在实践中依然有效。相比原有方法， extbf{DAPS++} 需要更少的函数求值（NFEs）和测量优化步数，在多种图像修复任务中均实现高计算效率与鲁棒重建性能。
原文摘要 · Abstract (English)
From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide the sampling process. However, this formulation fails to explain its practical behavior: the prior offers limited guidance, while reconstruction is largely driven by the measurement-consistency term, leading to an inference process that is effectively decoupled from the diffusion dynamics. We show that the diffusion prior in these solvers functions primarily as a warm initializer that places estimates near the data manifold, while reconstruction is driven almost entirely by measurement consistency. Based on this observation, we introduce \textbf{DAPS++}, which fully decouples diffusion-based initialization from likelihood-driven refinement, allowing the likelihood term to guide inference more directly while maintaining numerical stability and providing insight into why unified diffusion trajectories remain effective in practice. By requiring fewer function evaluations (NFEs) and measurement-optimization steps, \textbf{DAPS++} achieves high computational efficiency and robust reconstruction performance across diverse image restoration tasks.
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。