HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
Lingbo Yang, Chang Liu, Pan Wang, Shanshe Wang, Peiran Ren, Siwei Ma, Wen Gao
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Lotayou/Face-RenovationOfficialIn paperpytorch★ 292
- github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGANmindspore★ 0
- github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGANmindspore★ 0
- github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGANmindspore★ 0
- github.com/Mind23-2/MindCode-3/tree/main/HiFaceGANmindspore★ 0
Abstract
Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with heterogeneous degradations and rich background contents. In this paper, we investigate the 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 formulated 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 HiFaceGAN over a wide range of challenging restoration subtasks, demonstrating its versatility, robustness and generalization ability towards real-world face processing applications.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| CelebA-Test | HiFaceGAN | LPIPS | 47.7 | — | Unverified |