mlsanityData to 14 Oct 2026

NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results

arXiv 2504.14600 ↗First posted 20 Apr 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural, realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. The track of the challenge evaluates performance using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 141 registrants, with 13 teams submitting valid models, and ultimately, 10 teams achieved a valid score in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 58 of its 89 references that are in the map. First posted on arXiv 20 Apr 2025.

Builds on

58 of 89 references.

References · 58

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  7. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  8. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  9. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  10. 2023Adversarial Diffusion Distillationcited by 759
  11. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  12. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
38 more
  1. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  2. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
  3. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  4. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  5. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  6. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  7. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 286
  8. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  9. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  10. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 258
  11. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 257
  12. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 246
  13. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
  14. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 209
  15. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  16. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  17. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  18. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  19. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 100
  20. 2020Progressive Semantic-Aware Style Transformation for Blind Face Restorationcited by 99
  21. 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 97
  22. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 97
  23. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 87
  24. 2018Deep Semantic Face Deblurringcited by 80
  25. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
  26. 2019Progressive Face Super-Resolution via Attention to Facial Landmarkcited by 73
  27. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  28. 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidancecited by 49
  29. 2024NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 40
  30. 2023RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairscited by 33
  31. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  32. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  33. 2025The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Reportcited by 26
  34. 2025NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Resultscited by 25
  35. 2023Dual Associated Encoder for Face Restorationcited by 23
  36. 2023Towards Real-World Blind Face Restoration with Generative Diffusion Priorcited by 22
  37. 2025NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 22
  38. 2025The Tenth NTIRE 2025 Image Denoising Challenge Reportcited by 21

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 1.

10 papers.

  1. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  2. 2025NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Resultscited by 12
  3. 2025NTIRE 2025 challenge on Text to Image Generation Model Quality Assessmentcited by 8
  4. 2025NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challengecited by 5
  5. 2025RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Reportcited by 4
  6. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  7. 2025HonestFace: Towards Honest Face Restoration with One-Step Diffusion Modelcited by 1
  8. 2025NTIRE 2025 Image Shadow Removal Challenge Reportcited by 1
  9. 2025NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Resultscited by 1
  10. 2026The Third Challenge on Image Denoising at NTIRE 2026: Methods and Resultscited by 1