mlsanityData to 14 Oct 2026

The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results

arXiv 2604.10532 ↗First posted 12 Apr 2026cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural and 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. Performance is evaluated using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 96 registrants, with 10 teams submitting valid models; ultimately, 9 teams achieved valid scores 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 13 papers in the map (data through 14 Oct 2026). Builds on 54 of its 86 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

54 of 86 references.

References · 54

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  10. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  11. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  12. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
38 more
  1. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  2. 2023Adversarial Diffusion Distillationcited by 759
  3. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  4. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  5. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  7. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
  8. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  9. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  10. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 277
  11. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 246
  12. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
  13. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  14. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  15. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  16. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  17. 2020Progressive Semantic-Aware Style Transformation for Blind Face Restorationcited by 99
  18. 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 97
  19. 2018Deep Semantic Face Deblurringcited by 80
  20. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
  21. 2019Progressive Face Super-Resolution via Attention to Facial Landmarkcited by 73
  22. 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidancecited by 49
  23. 2023RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairscited by 33
  24. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  25. 2026The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Reportcited by 25
  26. 2023Dual Associated Encoder for Face Restorationcited by 23
  27. 2023Towards Real-World Blind Face Restoration with Generative Diffusion Priorcited by 22
  28. 2024WaveFace: Authentic Face Restoration with Efficient Frequency Recoverycited by 20
  29. 2023DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restorationcited by 17
  30. 2024ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restorationcited by 16
  31. 2026NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Resultscited by 16
  32. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)cited by 16
  33. 2025OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolutioncited by 15
  34. 2026NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methodscited by 15
  35. 2025FaceMe: Robust Blind Face Restoration with Personal Identificationcited by 14
  36. 2024BVI-AOM: A New Training Dataset for Deep Video Compression Optimizationcited by 12
  37. 2024Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Modelcited by 12
  38. 2025InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restorationcited by 9

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

  1. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  2. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)cited by 12
  3. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)cited by 12
  4. 2026The Fourth Challenge on Image Super-Resolution (×4) at NTIRE 2026: Benchmark Results and Method Overviewcited by 10
  5. 2026NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Reportcited by 8
  6. 2026Low Light Image Enhancement Challenge at NTIRE 2026cited by 7
  7. 2026The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overviewcited by 7
  8. 2026The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overviewcited by 6
  9. 2026Robust Deepfake Detection, NTIRE 2026 Challenge: Reportcited by 6
  10. 2026The First Controllable Bokeh Rendering Challenge at NTIRE 2026cited by 2
  11. 2026The Third Challenge on Image Denoising at NTIRE 2026: Methods and Resultscited by 1
  12. 2026NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Resultscited by 0
1 more
  1. 2026NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challengecited by 0