HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment

By Lingbo Yang, Chang Liu, Pan Wang, Shanshe Wang, Peiran Ren, Siwei Ma, Wen Gao. 2020

154 citations recorded by the source corpus.

Existing face restoration researches typically rely on either the image degradation prior or explicit guidance labels for training, which often lead to limited generalization ability over real-world images with heterogeneous degradation and rich background contents. In this paper, we investigate a more challenging and practical "dual-blind" version of the problem by lifting the requirements on both types of prior, termed as "Face Renovation"(FR). Specifically, we formulate FR as a semantic-guided generation problem and tackle it with a collaborative suppression and replenishment (CSR) approach. This leads to HiFaceGAN, a multi-stage framework containing several nested CSR units that progressively replenish facial details based on the hierarchical semantic guidance extracted from the front-end content-adaptive suppression modules. Extensive experiments on both synthetic and real face images have verified the superior performance of our HiFaceGAN over a wide range of challenging restoration subtasks, demonstrating its versatility, robustness and generalization ability towards real-world face processing applications. Code is available at https://github.com/Lotayou/Face-Renovation.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Chen Change Loy
3. Ming-Hsuan Yang
4. Lei Zhang
5. Dacheng Tao
6. Yu Qiao
7. Ying Shan
8. Xiaogang Wang

In Generative Models

1. David J. Fleet
2. Jonathan Ho
3. Mohammad Norouzi
4. Chitwan Saharia
5. Ying Shan
6. William Chan
7. Tim Salimans
8. Xintao Wang

Citations in the corpus

• Image Super-Resolution via Iterative Refinement (2021, background): “GAN-based super-resolution methods have also found considerable success [12], [16], [17], [30], [31], [32], [59].”
• GAN Prior Embedded Network for Blind Face Restoration in the Wild (2021, methodology): “[47] proposed a collaborative suppression and replenishment (CSR) approach to progressively replenish facial details.”
• Towards Robust Blind Face Restoration with Codebook Lookup Transformer (2022, unknown): “Some methods introduce facial landmarks [5], face parsing maps [4, 29, 40], facial component heatmaps [43], or 3D shapes [15, 27, 45] in their designs.”
• Towards Real-World Blind Face Restoration with Generative Facial Prior (2021, methodology): “We compare our GFP-GAN with several state-of-the-art face restoration methods: HiFaceGAN [69], DFDNet [46], PSFRGAN [6], Super-FAN [4] and Wan et al.”