mlsanityData to 14 Oct 2026

NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results

arXiv 2504.14582 ↗First posted 20 Apr 2025cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper presents the NTIRE 2025 image super-resolution (×4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a ×4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 77 of its 123 references that are in the map. First posted on arXiv 20 Apr 2025.

Builds on

77 of 123 references.

References · 77

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  12. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
38 more
  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  2. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  4. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  5. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  6. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  7. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  8. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  9. 2024VMamba: Visual State Space Modelcited by 969
  10. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  11. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  12. 2022Simple Baselines for Image Restorationcited by 708
  13. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  14. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  15. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 352
  16. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  17. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  18. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 255
  19. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  20. 2024Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrencecited by 159
  21. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  22. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 108
  23. 2024MambaIRv2: Attentive State Space Restorationcited by 94
  24. 2018Gated Context Aggregation Network for Image Dehazing and Derainingcited by 89
  25. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 87
  26. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 86
  27. 2024FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mambacited by 81
  28. 2024Diffusion Models in Low-Level Vision: A Surveycited by 74
  29. 2022SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolutioncited by 68
  30. 2024Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionarycited by 64
  31. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 60
  32. 2024Retinexmamba: Retinex-based Mamba for Low-light Image Enhancementcited by 59
  33. 2024FreqMamba: Viewing Mamba from a Frequency Perspective for Image Derainingcited by 57
  34. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  35. 2024RainMamba: Enhanced Locality Learning with State Space Models for Video Derainingcited by 56
  36. 2024MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Spacecited by 48
  37. 2024HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolutioncited by 42
  38. 2024U-shaped Vision Mamba for Single Image Dehazingcited by 40

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 12.

12 papers.

  1. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 16
  2. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  3. 2025NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Resultscited by 12
  4. 2025HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Accelerationcited by 12
  5. 2025NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Resultscited by 9
  6. 2025NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolutioncited by 9
  7. 2025NTIRE 2025 challenge on Text to Image Generation Model Quality Assessmentcited by 8
  8. 2025NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challengecited by 5
  9. 2025RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Reportcited by 4
  10. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  11. 2025NTIRE 2025 Image Shadow Removal Challenge Reportcited by 1
  12. 2025NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Resultscited by 1