Browse State-of-the-Art › Blind Face Restoration
Blind Face Restoration
29 papers with code · 4 benchmarks · 5 datasets archive 2025-07-28
Blind face restoration aims at recovering high-quality faces from the low-quality counterparts suffering from unknown degradation, such as low-resolution, noise, blur, compression artifacts, etc. When applied to real-world scenarios, it becomes more challenging, due to more complicated degradation, diverse poses and expressions.
Description source: Towards Real-World Blind Face Restoration with Generative Facial Prior
Image source: Towards Real-World Blind Face Restoration with Generative Facial Prior
Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CelebA-Test (15 rows) | CodeFormer | Towards Robust Blind Face Restoration with Codebook Lookup Transformer | code | — | Compare |
| LFW (9 rows) | DiffBIR | DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior | code | — | Compare |
| WIDER (9 rows) | DiffBIR | DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior | code | — | Compare |
| CelebA-HQ (6 rows) | GPEN | GAN Prior Embedded Network for Blind Face Restoration in the Wild | code | Syntology official (archive's flag): 16 ran · 16 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
5 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 55 · with a code link: 29 · where Syntology ran a sample: 11 (8 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (11 of 55 tagged: 8 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 55 of 55, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
10 Aug 2019 6 repositories listedWe present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.
-
11 May 2020 5 repositories listedExisting 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…
-
13 May 2021 3 repositories listed Syntology official (archive's flag): 16 ran · 16 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified (of 21 harvested samples) · 21 pointer-only (licence)The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results.
-
29 Aug 2023 2 repositories listedWe present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks in a unified framework.
-
13 Dec 2022 2 repositories listedMoreover, the transition distribution can contract the error of the restoration backbone and thus makes our method more robust to unknown degradations.
-
8 Jun 2022 2 repositories listedTo address this problem, we first synthesize two blind face restoration benchmark datasets called EDFace-Celeb-1M (BFR128) and EDFace-Celeb-150K (BFR512).
-
30 Dec 2024 1 repository listedBlind face restoration aims to recover high-quality facial images from various unidentified sources of degradation, posing significant challenges due to the minimal information retrievable from the degraded images.
-
21 Nov 2024 1 repository listedRestorerID is a diffusion model-based method that restores low-quality images with varying levels of degradation by using a single reference image.
-
13 Oct 2024 1 repository listedIn this paper, we propose a novel framework, namely AuthFace that achieves highly authentic face restoration results by exploring a face-oriented generative diffusion prior.
-
1 Oct 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 4 pointer-only (licence)Photo-realistic image restoration algorithms are typically evaluated by distortion measures (e. g., PSNR, SSIM) and by perceptual quality measures (e. g., FID, NIQE), where the desire is to attain the lowest possible…
-
2 Sep 2024 1 repository listedTo inherit the exceptional realism generative ability of the diffusion model and also constrained by the identity-aware fidelity, we propose a novel diffusion-based framework by embedding the 3D facial priors as…
-
12 Mar 2024 1 repository listedWhile diffusion-based image restoration (IR) methods have achieved remarkable success, they are still limited by the low inference speed attributed to the necessity of executing hundreds or even thousands of sampling…
-
25 Dec 2023 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 4 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified (of 16 harvested samples) · 6 pointer-only (licence)We propose BFRffusion which is thoughtfully designed to effectively extract features from low-quality face images and could restore realistic and faithful facial details with the generative prior of the pretrained…
-
14 Aug 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 5 pointer-only (licence)Restoring facial details from low-quality (LQ) images has remained a challenging problem due to its ill-posedness induced by various degradations in the wild.
-
14 Aug 2023 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified (of 12 harvested samples) · 7 pointer-only (licence)In this work, we propose RestoreFormer++, which on the one hand introduces fully-spatial attention mechanisms to model the contextual information and the interplay with the priors, and on the other hand, explores an…
-
18 Jul 2023 1 repository listedAnd with the coarse video, our method synthesizes a coarse talking head avatar with a deforming neural radiance field.
-
13 Mar 2023 1 repository listed Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)However, it is expensive and infeasible to include every type of degradation to cover real-world cases in the training data.
-
15 Oct 2022 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)Generally, it is a challenging and intractable task to improve the photo-realistic performance of blind restoration and adaptively handle the generic and specific restoration scenarios with a single unified model.
-
28 Jun 2022 1 repository listedTo this end, we propose a Face Restoration Searching Network (FRSNet) to adaptively search the suitable feature extraction architecture within our specified search space, which can directly contribute to the restoration…
-
22 Jun 2022 1 repository listedIn this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction…
-
13 May 2022 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 15 pointer-only (licence)Equipped with the VQ codebook as a facial detail dictionary and the parallel decoder design, the proposed VQFR can largely enhance the restored quality of facial details while keeping the fidelity to previous methods.
-
17 Jan 2022 1 repository listed Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 1 pointer-only (licence)Blind face restoration is to recover a high-quality face image from unknown degradations.
-
11 Jan 2021 1 repository listedBlind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.
-
12 Oct 2020 1 repository listedFace restoration is an inherently ill-posed problem, where additional prior constraints are typically considered crucial for mitigating such pathology.
-
18 Sep 2020 1 repository listedCompared with previous networks, the proposed PSFR-GAN makes full use of the semantic (parsing maps) and pixel (LQ images) space information from different scales of input pairs.
-
2 Aug 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature…
-
1 Jun 2020 1 repository listedFirst, given a degraded observation, we select the optimal guidance based on the weighted affine distance on landmark sets, where the landmark weights are learned to make the guidance image optimized to HQ image…
-
15 Dec 2019 1 repository listedSuch an over-parameterization of the latent space significantly improves the image reconstruction quality, outperforming existing competitors.
-
13 Apr 2018 1 repository listedFor better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network…
-
LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter29 May 2025 0 repositories listedBlind face restoration from low-quality (LQ) images is a challenging task that requires not only high-fidelity image reconstruction but also the preservation of facial identity.
-
TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration26 Mar 2025 0 repositories listed
-
IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond12 Mar 2025 0 repositories listed
-
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration4 Feb 2025 0 repositories listed
-
InfoBFR: Real-World Blind Face Restoration via Information Bottleneck26 Jan 2025 0 repositories listed
-
Binary Diffusion Probabilistic Model23 Jan 2025 0 repositories listed
-
FaceMe: Robust Blind Face Restoration with Personal Identification9 Jan 2025 0 repositories listed
-
Dynamic Content Prediction with Motion-aware Priors for Blind Face Video Restoration1 Jan 2025 0 repositories listed
-
DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration15 Nov 2024 0 repositories listed
-
Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos15 Oct 2024 0 repositories listed
-
6 Oct 2024 0 repositories listed
-
Towards Real-world Video Face Restoration: A New Benchmark30 Apr 2024 0 repositories listed
-
WaveFace: Authentic Face Restoration with Efficient Frequency Recovery19 Mar 2024 0 repositories listed
-
DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration15 Mar 2024 0 repositories listed
-
BFRFormer: Transformer-based generator for Real-World Blind Face Restoration29 Feb 2024 0 repositories listed
-
CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models8 Feb 2024 0 repositories listed
-
ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-based Blind Face Restoration13 Jan 2024 0 repositories listed
-
Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration1 Jan 2024 0 repositories listed
-
Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer20 Aug 2023 0 repositories listed
-
Boosting Cross-Quality Face Verification using Blind Face Restoration15 Aug 2023 0 repositories listed
-
18 Jul 2023 0 repositories listed Syntology 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 (of 5 harvested samples) · 5 pointer-only (licence)
-
DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration8 May 2023 0 repositories listed
-
FaceFormer: Scale-aware Blind Face Restoration with Transformers20 Jul 2022 0 repositories listed
-
Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior28 May 2022 0 repositories listed
-
Blind Face Restoration via Integrating Face Shape and Generative Priors1 Jan 2022 0 repositories listed
-
Universal Face Restoration With Memorized Modulation3 Oct 2021 0 repositories listed
Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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