用统一梯度流实现低计算量高精度图像逆问题求解
Consistency Regularised Gradient Flows for Inverse Problems
- 构建欧氏-沃瑟斯坦2型梯度流，联合采样与提示优化
- 仅需少量迭代步数（low-NFE），重建质量优于现有方法
- 适合需要快速生成的医学成像、遥感等实时应用
视觉-语言潜在扩散模型（LDM）为图像逆问题提供了强大的生成先验。然而，现有的基于LDM的求解器通常需要大量神经网络函数评估（NFE）并反向传播通过大型预训练组件，导致计算成本高昂，且在某些情况下重建质量下降。本文提出一种统一的欧氏-沃瑟斯坦2型梯度流框架，通过单一流在潜在空间中联合执行后验采样与提示优化，使先验与后验与观测数据对齐。结合少步数的潜在文本到图像模型，该方法实现了无需反向传播通过自编码器的低NFE推理。在多个经典成像逆问题上的实验表明，本方法在显著降低计算开销的同时达到当前最优性能。
原文摘要 · Abstract (English)
Vision-Language Latent Diffusion Models (LDMs) (Rombach et al., 2022) provide powerful generative priors for inverse problems. However, existing LDM-based inverse solvers typically require a large number of neural function evaluations (NFEs) and backpropagation through large pretrained components, leading to substantial computational costs and, in some cases, degraded reconstruction quality. We propose a unified Euclidean-Wasserstein-2 gradient-flow framework that jointly performs posterior sampling and prompt optimization in the latent space through a single flow that aligns the prior and posterior with the observed data. Combined with few-step latent text-to-image models, this formulation enables low-NFE inference without backpropagation through autoencoders. Experiments across several canonical imaging inverse problems show that our method achieves state-of-the-art performance with significantly reduced computational cost.
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。