Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results (2404.09790v1)

Published 15 Apr 2024 in cs.CV

Abstract: This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (96)
  1. Unsplash Full Dataset 1.2.2. https://unsplash.com/data. Accessed: 2024-03-21.
  2. Single image super-resolution: a comprehensive review and recent insight. Frontiers of Computer Science, 2024.
  3. NTIRE 2024 dense and non-homogeneous dehazing challenge report. In CVPRW, 2024.
  4. NTIRE 2024 challenge on night photography rendering. In CVPRW, 2024.
  5. Retinexformer: One-stage retinex-based transformer for low-light image enhancement. In CVPR, 2023.
  6. Computer vision applied to super resolution. IEEE Signal Processing Magazine, 2003.
  7. Deep portrait quality assessment. a NTIRE 2024 challenge survey. In CVPRW, 2024.
  8. Real-world blind super-resolution via feature matching with implicit high-resolution priors. In ACM MM, 2022a.
  9. Simple baselines for image restoration. In ECCV, 2022b.
  10. Activating more pixels in image super-resolution transformer. CVPR, 2023a.
  11. Activating more pixels in image super-resolution transformer. In CVPR, 2023b.
  12. Mffn: image super-resolution via multi-level features fusion network. The Visual Computer, 2024a.
  13. Cross aggregation transformer for image restoration. In NeurIPS, 2022c.
  14. Dual aggregation transformer for image super-resolution. In ICCV, 2023c.
  15. Recursive generalization transformer for image super-resolution. In ICLR, 2024b.
  16. Deep raw image super-resolution. a NTIRE 2024 challenge survey. In CVPRW, 2024.
  17. Reparameterized residual feature network for lightweight image super-resolution. In CVPR, 2023.
  18. Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks. In CVPR, 2019.
  19. Image super-resolution using deep convolutional networks. TPAMI, 2016.
  20. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR, 2021.
  21. Example-based super-resolution. IEEE Computer graphics and Applications, 2002.
  22. Dw-gan: A discrete wavelet transform gan for nonhomogeneous dehazing. In CVPR, 2021.
  23. Total-body low-dose ct image denoising using a prior knowledge transfer technique with a contrastive regularization mechanism. Medical Physics, 2023a.
  24. Oif-net: An optical flow registration-based pet/mr cross-modal interactive fusion network for low-count brain pet image denoising. TMI, 2023b.
  25. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752, 2023a.
  26. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752, 2023b.
  27. Data acquisition and preparation for dual-reference deep learning of image super-resolution. TIP, 2022.
  28. Deep residual learning for image recognition. In CVPR, 2016.
  29. An overview of wavelet based multiresolution analyses. SIAM Review, 1994.
  30. Ntire 2022 challenge on efficient super-resolution: Methods and results. In CVPRW, 2022.
  31. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  32. Segment anything. In ICCV, 2023.
  33. Residual local feature network for efficient super-resolution. In CVPR, 2022.
  34. Training transformer models by wavelet losses improves quantitative and visual performance in single image super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  35. Deep laplacian pyramid networks for fast and accurate super-resolution. In CVPR, 2017.
  36. Photo-realistic single image super-resolution using a generative adversarial network. In CVPR, 2017.
  37. NTIRE 2024 challenge on short-form UGC video quality assessment: Methods and results. In CVPRW, 2024.
  38. The heterogeneity hypothesis: Finding layer-wise differentiated network architectures. In CVPR, 2021.
  39. Efficient and explicit modelling of image hierarchies for image restoration. In CVPR, 2023a.
  40. Lsdir: A large scale dataset for image restoration. In CVPRW, 2023b.
  41. Swinir: Image restoration using swin transformer. In ICCVW, 2021.
  42. NTIRE 2024 restore any image model (RAIM) in the wild challenge. In CVPRW, 2024.
  43. Enhanced deep residual networks for single image super-resolution. In CVPRW, 2017a.
  44. Enhanced deep residual networks for single image super-resolution. In CVPRW, 2017b.
  45. Blind image super-resolution: A survey and beyond. TPAMI, 2022.
  46. Residual feature aggregation network for image super-resolution. In CVPR, 2020.
  47. NTIRE 2024 quality assessment of AI-generated content challenge. In CVPRW, 2024a.
  48. NTIRE 2024 challenge on low light image enhancement: Methods and results. In CVPRW, 2024b.
  49. Vmamba: Visual state space model. arXiv preprint arXiv:2401.10166, 2024c.
  50. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, 2021.
  51. And: Adversarial neural degradation for learning blind image super-resolution. NeurIPS, 2024.
  52. Stephane Mallat. Wavelets for a vision. Proceedings of the IEEE, 1996.
  53. Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178, 2021.
  54. Image super-resolution with non-local sparse attention. In CVPR, 2021.
  55. Space-time super-resolution using graph-cut optimization. TPAMI, 2011.
  56. Single image super-resolution via a holistic attention network. In ECCV, 2020.
  57. Super-resolution of omnidirectional images using adversarial learning. In MMSP, 2019.
  58. Evidence-based framework for multi-image super-resolution. In ICACNI, 2018.
  59. Generalizing the nonlocal-means to super-resolution reconstruction. TIP, 2008.
  60. Learning transferable visual models from natural language supervision. In ICML, 2021.
  61. The ninth NTIRE 2024 efficient super-resolution challenge report. In CVPRW, 2024.
  62. High-resolution image synthesis with latent diffusion models. In CVPR, 2022.
  63. Enhancenet: Single image super-resolution through automated texture synthesis. In ICCV, 2017.
  64. Efficientnet: Rethinking model scaling for convolutional neural networks. In ICML, 2019.
  65. Seven ways to improve example-based single image super resolution. In CVPR, 2016.
  66. Ntire 2017 challenge on single image super-resolution: Methods and results. In CVPRW, 2017.
  67. Deep super-resolution network for single image super-resolution with realistic degradations. In Proceedings of the 13th International Conference on Distributed Smart Cameras, 2019.
  68. NTIRE 2024 image shadow removal challenge report. In CVPRW, 2024.
  69. Attention is all you need. NeurIPS, 2017.
  70. Swift parameter-free attention network for efficient super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  71. NTIRE 2024 challenge on stereo image super-resolution: Methods and results. In CVPRW, 2024a.
  72. Esrgan: Enhanced super-resolution generative adversarial networks. In ECCVW, 2018.
  73. Real-esrgan: Training real-world blind super-resolution with pure synthetic data. In ICCVW, 2021.
  74. NTIRE 2024 challenge on light field image super-resolution: Methods and results. In CVPRW, 2024b.
  75. Deep learning for image super-resolution: A survey. TPAMI, 2020.
  76. Component divide-and-conquer for real-world image super-resolution. In ECCV, 2020.
  77. HQ-50K: A large-scale, high-quality dataset for image restoration. CoRR, 2023.
  78. NTIRE 2024 challenge on blind enhancement of compressed image: Methods and results. In CVPRW, 2024.
  79. Deep learning for single image super-resolution: A brief review. TMM, 2019.
  80. A two-branch neural network for non-homogeneous dehazing via ensemble learning. In CVPR, 2021.
  81. NTIRE 2024 challenge on HR depth from images of specular and transparent surfaces. In CVPRW, 2024.
  82. Restormer: Efficient transformer for high-resolution image restoration. In CVPR, 2022.
  83. Swinfir: Revisiting the swinir with fast fourier convolution and improved training for image super-resolution. arXiv preprint arXiv:2208.11247, 2022a.
  84. Accurate image restoration with attention retractable transformer. In ICLR, 2023a.
  85. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. TIP, 2017.
  86. Designing a practical degradation model for deep blind image super-resolution. In ICCV, 2021.
  87. Efficient long-range attention network for image super-resolution. In ECCV, 2022b.
  88. Image super-resolution using very deep residual channel attention networks. In ECCV, 2018.
  89. Residual non-local attention networks for image restoration. In ICLR, 2019.
  90. Recognize anything: A strong image tagging model. CoRR, 2023b.
  91. Ntire 2023 challenge on image super-resolution (x4): Methods and results. In CVPRW, 2023c.
  92. NTIRE 2024 challenge on bracketing image restoration and enhancement: Datasets, methods and results. In CVPRW, 2024.
  93. Quality-aware pretrained models for blind image quality assessment. In CVPR, 2023a.
  94. Zoom-vqa: Patches, frames and clips integration for video quality assessment. In CVPRW, 2023b.
  95. Cross-scale internal graph neural network for image super-resolution. In NeurIPS, 2020.
  96. Learning transferable architectures for scalable image recognition. In CVPR, 2018.
Citations (24)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now