FaiResGAN: Fair and robust blind face restoration with biometrics preservation

Modern computer vision technologies enable systems to detect, recognize, and analyze facial features, but challenges arise when images are noisy, blurred, or low quality. Blind face restoration, which aims to recover high-quality facial images without prior knowledge of degradation, addresses this issue. In this paper, we introduce Fair Restoration GAN (FaiResGAN), a novel Generative Adversarial Network (GAN) designed to balance face restoration with the preservation of soft biometrics (identity, ethnicity, age, and gender). Our model incorporates a pseudo-random batch composition algorithm to promote fairness and mitigate bias, alongside a realistic degradation model simulating corruptions typical in surveillance images. Experimental results show that FaiResGAN outperforms state-of-the-art blind face restoration methods, both quantitatively and qualitatively. A user study involving 40 participants showed that FaiResGAN-restored images were preferred by 70% of users. Additionally, tests on VGGFace2, UTKFace, and FairFace datasets demonstrate FaiResGAN’s superior performance in preserving soft biometric attributes and ensuring fair restoration across different genders and ethnicities. • FaiResGAN preserves facial biometrics via a novel identity-aware loss function. • Balanced batch composition improves fairness in facial restoration. • A tailored degradation model simulates real-world corruptions in facial images. • FaiResGAN outperforms PSFRGAN, GPEN, RestoreFormer, and GFPGAN. • A user study shows ∼ 70 % of participants prefer FaiResGAN restorations over GFPGAN.