Towards Unsupervised Blind Face Restoration using Diffusion Prior

TL;DR

This paper introduces an unsupervised method for blind face restoration that leverages a diffusion prior during training to enhance perceptual quality without affecting inference efficiency.

Contribution

It proposes a novel training approach using a diffusion model as a generative prior to fine-tune restoration models with unknown degradations, without relying on ground truth images.

Findings

Achieves state-of-the-art results on synthetic and real-world datasets.

Improves perceptual quality of existing blind face restoration models.

Maintains efficient inference by only using diffusion models during training.

Abstract

Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a handcrafted image degradation pipeline. The models trained on such synthetic degradations, however, cannot deal with inputs of unseen degradations. In this paper, we address this issue by using only a set of input images, with unknown degradations and without ground truth targets, to fine-tune a restoration model that learns to map them to clean and contextually consistent outputs. We utilize a pre-trained diffusion model as a generative prior through which we generate high quality images from the natural image distribution while maintaining the input image content through consistency constraints. These generated images are then used as pseudo targets to fine-tune a pre-trained restoration model. Unlike many recent approaches that employ diffusion models at test time, we only do so during training and thus maintain an efficient inference-time performance. Extensive experiments show that the proposed approach can consistently improve the perceptual quality of pre-trained blind face restoration models while maintaining great consistency with the input contents. Our best model also achieves the state-of-the-art results on both synthetic and real-world datasets.