用扩散模型做逆问题求解,无需训练就能高效恢复图像。
A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models
- 在隐空间构建带正则的Wasserstein梯度流,实现无训练优化。
- 在标准测试上优于传统方法,恢复图像质量显著提升。
- 适合图像重建、超分辨率等需强先验的任务场景。
求解病态逆问题需要强大且灵活的先验。本文提出一种无需训练的新方法——扩散正则化沃瑟斯坦梯度流(DWGF),利用预训练的隐空间扩散模型作为先验。具体地,将后验采样问题建模为隐空间中相对熵的正则化沃瑟斯坦梯度流。我们在标准基准测试中使用StableDiffusion(Rombach et al., 2022)作为先验,验证了该方法的有效性。
原文摘要 · Abstract (English)
Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this task through a new training-free approach, termed Diffusion-regularized Wasserstein Gradient Flow (DWGF). Specifically, we formulate the posterior sampling problem as a regularized Wasserstein gradient flow of the Kullback-Leibler divergence in the latent space. We demonstrate the performance of our method on standard benchmarks using StableDiffusion (Rombach et al., 2022) as the prior.
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。