通过受限先验进行生成式恢复

摘要

去噪扩散模型固有的生成能力使其非常适用于图像恢复任务，其目标是在生成空间中找到与输入图像紧密相似的最佳高质量图像。我们提出了一种方法，通过简单地向待恢复的输入图像添加噪声，然后去噪来调整预训练的扩散模型以用于图像恢复。我们的方法基于这样一个观察：生成模型的空间需要受到约束。我们通过对捕捉输入图像特征的一组锚定图像对生成模型进行微调来施加这种约束。有了受约束的空间，我们可以利用用于生成的采样策略来进行图像恢复。我们针对先前的方法进行评估，并在多个真实世界的恢复数据集上展示出卓越的性能，能够保留身份和图像质量。我们还展示了一个重要且实用的个性化恢复应用，其中我们使用个人相册作为锚定图像来约束生成空间。这种方法使我们能够产生能够准确保留高频细节的结果，而先前的工作无法做到。项目网页：https://gen2res.github.io。

English

The inherent generative power of denoising diffusion models makes them well-suited for image restoration tasks where the objective is to find the optimal high-quality image within the generative space that closely resembles the input image. We propose a method to adapt a pretrained diffusion model for image restoration by simply adding noise to the input image to be restored and then denoise. Our method is based on the observation that the space of a generative model needs to be constrained. We impose this constraint by finetuning the generative model with a set of anchor images that capture the characteristics of the input image. With the constrained space, we can then leverage the sampling strategy used for generation to do image restoration. We evaluate against previous methods and show superior performances on multiple real-world restoration datasets in preserving identity and image quality. We also demonstrate an important and practical application on personalized restoration, where we use a personal album as the anchor images to constrain the generative space. This approach allows us to produce results that accurately preserve high-frequency details, which previous works are unable to do. Project webpage: https://gen2res.github.io.

通过受限先验进行生成式恢复

Restoration by Generation with Constrained Priors

摘要

Support