用数据一致性约束提升扩散模型逆问题求解精度
Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint
- 在反向生成过程中引入数据一致性约束，优化早期误差
- 在FFHQ和ImageNet上实现优于现有方法的重建准确率
- 适用于线性和非线性逆问题，支持潜空间与Tweedie公式
扩散模型在通过后验采样解决逆问题方面表现优异，但在早期步骤中存在误差。尽管最近提出了若干解耦后验采样方法，但其反向过程忽略了测量信息，导致误差阻碍后续优化。为此，我们提出引导式解耦后验采样（GDPS），在反向过程中集成数据一致性约束，使优化过程过渡更平滑，促进更有效收敛至目标分布。此外，我们将方法扩展至潜空间扩散模型和Tweedie公式，验证其可扩展性。我们在FFHQ和ImageNet数据集上，针对多种线性和非线性任务，在标准及挑战性条件下评估了GDPS。实验结果表明，该方法达到当前最优性能，显著提升了重建精度。
原文摘要 · Abstract (English)
Diffusion models have shown strong performances in solving inverse problems through posterior sampling while they suffer from errors during earlier steps. To mitigate this issue, several Decoupled Posterior Sampling methods have been recently proposed. However, the reverse process in these methods ignores measurement information, leading to errors that impede effective optimization in subsequent steps. To solve this problem, we propose Guided Decoupled Posterior Sampling (GDPS) by integrating a data consistency constraint in the reverse process. The constraint performs a smoother transition within the optimization process, facilitating a more effective convergence toward the target distribution. Furthermore, we extend our method to latent diffusion models and Tweedie's formula, demonstrating its scalability. We evaluate GDPS on the FFHQ and ImageNet datasets across various linear and nonlinear tasks under both standard and challenging conditions. Experimental results demonstrate that GDPS achieves state-of-the-art performance, improving accuracy over existing methods.
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。