Papers › Towards Real-World Blind Face Restoration with Generative Facial Prior

Towards Real-World Blind Face Restoration with Generative Facial Prior

11 Jan 2021CVPR 2021 1arXiv:2101.04061archive 2025-07-28

Xintao Wang, Yu Li, Honglun Zhang, Ying Shan

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Thanks to the powerful generative facial prior and delicate designs, our GFP-GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require expensive image-specific optimization at inference. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real-world datasets.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

TencentARC/GFPGAN officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond (arXiv:2307.08996; that paper's own run record: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Blind Face RestorationVideo Super-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blind Face Restoration CelebA-Test GFP-GAN Deg. 34.60 #2 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test GFP-GAN FID 42.62 #2 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test GFP-GAN LPIPS 36.46 #2 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test GFP-GAN NIQE 4.077 #2 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test GFP-GAN PSNR 25.08 #2 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test GFP-GAN SSIM 0.6777 #2 of 15 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN 1 - LPIPS 0.793 #30 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN ERQAv1.0 0.538 #30 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN FPS 1.562 #30 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN PSNR 24.195 #30 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN QRCRv1.0 0 #30 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN SSIM 0.745 #30 of 32 Archive leaderboard report
Video Super-Resolution MSU Video Super Resolution Benchmark: Detail Restoration GFPGAN Subjective score 2.686 #30 of 32 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adaptive Instance NormalizationConcatenated Skip ConnectionConvolutionDense ConnectionsFeedforward NetworkGFP-GANMax PoolingR1 RegularizationReLUSpatial Feature TransformStyleGANU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections