HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
This work addresses the challenge of real-world face processing with heterogeneous degradations, offering a versatile and robust solution for applications in image restoration.
The paper tackles the problem of face restoration without relying on degradation priors or explicit guidance labels, proposing HiFaceGAN which achieves superior performance on synthetic and real face images across various restoration subtasks.
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.