SOTAVerified

Blind Face Restoration

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 55 papers

TitleStatusHype
Visual Style Prompt Learning Using Diffusion Models for Blind Face RestorationCode1
FaceMe: Robust Blind Face Restoration with Personal Identification—0
Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos—0
Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior—0
ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-based Blind Face Restoration—0
FaceFormer: Scale-aware Blind Face Restoration with Transformers—0
CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models—0
Towards Real-world Video Face Restoration: A New Benchmark—0
InfoBFR: Real-World Blind Face Restoration via Information Bottleneck—0
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration—0
IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond—0
LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter—0
Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration—0
Towards Unsupervised Blind Face Restoration using Diffusion Prior—0
Boosting Cross-Quality Face Verification using Blind Face Restoration—0
Universal Face Restoration With Memorized Modulation—0
Blind Face Restoration via Integrating Face Shape and Generative Priors—0
Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer—0
WaveFace: Authentic Face Restoration with Efficient Frequency Recovery—0
DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration—0
TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration—0
DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration—0
Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond—0
Dynamic Content Prediction with Motion-aware Priors for Blind Face Video Restoration—0
DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration—0
Show:102550
← PrevPage 2 of 3Next →
All datasetsCelebA-TestLFWWIDERCelebA-HQ

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DFDNetLPIPS55.4—Unverified
2PULSELPIPS50.8—Unverified
3PSFRGANLPIPS50—Unverified
4GFPGANLPIPS49.5—Unverified
5HiFaceGANLPIPS47.7—Unverified
6VQFRLPIPS47.1—Unverified
7GLEANLPIPS46.9—Unverified
8mGANpriorLPIPS45.84—Unverified
9DiffBIRLPIPS45.73—Unverified
10DifFaceLPIPS43.5—Unverified
#ModelMetricClaimedVerifiedStatus
1PULSEFID64.86—Unverified
2DFDNetFID62.57—Unverified
3GPENFID57.58—Unverified
4GLEANFID53.49—Unverified
5CodeFormerFID52.02—Unverified
6PSFRGANFID51.89—Unverified
7GFP-GANFID49.96—Unverified
8DAEFRFID47.53—Unverified
9DiffBIRFID39.58—Unverified
#ModelMetricClaimedVerifiedStatus
1PULSEFID73.59—Unverified
2DFDNetFID57.84—Unverified
3PSFRGANFID51.16—Unverified
4GLEANFID47.11—Unverified
5GPENFID46.99—Unverified
6GFP-GANFID40.59—Unverified
7CodeFormerFID39.06—Unverified
8DAEFRFID36.72—Unverified
9DiffBIRFID32.35—Unverified
#ModelMetricClaimedVerifiedStatus
1Super-FANFID136.83—Unverified
2GWAInetFID135.84—Unverified
3GFRNetFID134.92—Unverified
4Pix2PixHDFID76.89—Unverified
5HiFaceGANFID56.67—Unverified
6GPENFID31.72—Unverified