PFStorer: Personalized Face Restoration and Super-Resolution
CVPR 2024(2024)
摘要
Recent developments in face restoration have achieved remarkable results in
producing high-quality and lifelike outputs. The stunning results however often
fail to be faithful with respect to the identity of the person as the models
lack necessary context. In this paper, we explore the potential of personalized
face restoration with diffusion models. In our approach a restoration model is
personalized using a few images of the identity, leading to tailored
restoration with respect to the identity while retaining fine-grained details.
By using independent trainable blocks for personalization, the rich prior of a
base restoration model can be exploited to its fullest. To avoid the model
relying on parts of identity left in the conditioning low-quality images, a
generative regularizer is employed. With a learnable parameter, the model
learns to balance between the details generated based on the input image and
the degree of personalization. Moreover, we improve the training pipeline of
face restoration models to enable an alignment-free approach. We showcase the
robust capabilities of our approach in several real-world scenarios with
multiple identities, demonstrating our method's ability to generate
fine-grained details with faithful restoration. In the user study we evaluate
the perceptual quality and faithfulness of the genereated details, with our
method being voted best 61
the votes.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要