Papers
Topics
Authors
Recent
Search
2000 character limit reached

NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results

Published 22 Apr 2024 in cs.CV | (2404.14248v1)

Abstract: This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (83)
  1. NTIRE 2024 dense and non-homogeneous dehazing challenge report. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  2. Ntire 2022 spectral recovery challenge and data set. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 863–881, 2022.
  3. Differentiable histogram loss functions for intensity-based image-to-image translation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  4. NTIRE 2024 challenge on night photography rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  5. Shiyin Wang Bin Xia, Yulun Zhang. Diffir: Efficient diffusion model for image restoration. In ICCV, 2023.
  6. Smooth maximum unit: Smooth activation function for deep networks using smoothing maximum technique. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 794–803, 2022.
  7. Learning photographic global tonal adjustment with a database of input/output image pairs. In CVPR 2011, pages 97–104. IEEE, 2011.
  8. Retinexformer: One-stage retinex-based transformer for low-light image enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12504–12513, 2023.
  9. Coarse-to-fine sparse transformer for hyperspectral image reconstruction. In ECCV, 2022.
  10. Mask-guided spectral-wise transformer for efficient hyperspectral image reconstruction. In CVPR, 2022.
  11. Mst++: Multi-stage spectral-wise transformer for efficient spectral reconstruction. In CVPRW, 2022.
  12. Degradation-aware unfolding half-shuffle transformer for spectral compressive imaging. In NeurIPS, 2022.
  13. Structure-aware sparse-view x-ray 3d reconstruction. In CVPR, 2024.
  14. Learning delicate local representations for multi-person pose estimation. In ECCV, 2020.
  15. Binarized spectral compressive imaging. In NeurIPS, 2023.
  16. Deep portrait quality assessment. a NTIRE 2024 challenge survey. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  17. Simple baselines for image restoration. In European conference on computer vision, pages 17–33, 2022.
  18. Simple baselines for image restoration. In Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner, editors, Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part VII, volume 13667 of Lecture Notes in Computer Science, pages 17–33. Springer, 2022.
  19. NTIRE 2024 challenge on image super-resolution (×4): Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  20. Improving image restoration by revisiting global information aggregation. In Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner, editors, Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part VII, volume 13667 of Lecture Notes in Computer Science, pages 53–71. Springer, 2022.
  21. Real-time under-display cameras image restoration and hdr on mobile devices. In Computer Vision – ECCV 2022 Workshops, volume 13802 of Lecture Notes in Computer Science. Springer, Cham, 2023.
  22. High-quality image restoration following human instructions. arXiv preprint arXiv:2401.16468, 2024.
  23. Deep raw image super-resolution. a NTIRE 2024 challenge survey. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  24. Lightnet: Generative model for enhancement of low-light images. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2231–2240, 2023.
  25. Depthcue: Restoration of underwater images using monocular depth as a clue. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, pages 196–205, January 2023.
  26. Aquagan: Restoration of underwater images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 296–304, June 2022.
  27. Total-body low-dose ct image denoising using a prior knowledge transfer technique with a contrastive regularization mechanism. Medical Physics, 50(5):2971–2984, 2023.
  28. Dw-gan: A discrete wavelet transform gan for nonhomogeneous dehazing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 203–212, 2021.
  29. A two-branch neural network for short-axis pet image quality enhancement. IEEE Journal of Biomedical and Health Informatics, 2023.
  30. Qlabgrad: A hyperparameter-free and convergence-guaranteed scheme for deep learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 12072–12081, 2024.
  31. Oif-net: An optical flow registration-based pet/mr cross-modal interactive fusion network for low-count brain pet image denoising. IEEE Transactions on Medical Imaging, 2023.
  32. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752, 2023.
  33. Zero-reference deep curve estimation for low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1780–1789, 2020.
  34. Zero-reference deep curve estimation for low-light image enhancement. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pages 1777–1786. Computer Vision Foundation / IEEE, 2020.
  35. Da-ae: Disparity-alleviation auto-encoder towards categorization of heritage images for aggrandized 3d reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5093–5100, 2022.
  36. Denoising diffusion probabilistic models. In Advances in neural information processing systems, volume 33, pages 6840–6851, 2020.
  37. Global structure-aware diffusion process for low-light image enhancement. Advances in Neural Information Processing Systems, 36, 2024.
  38. Low-light image enhancement with wavelet-based diffusion models. ACM Transactions on Graphics (TOG), 42(6):1–14, 2023.
  39. Adam: A method for stochastic optimization. In ICLR, 2015.
  40. Fast and accurate image super-resolution with deep laplacian pyramid networks. IEEE transactions on pattern analysis and machine intelligence, 41(11):2599–2613, 2018.
  41. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4681–4690, 2017.
  42. NTIRE 2024 challenge on short-form UGC video quality assessment: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  43. NTIRE 2024 restore any image model (RAIM) in the wild challenge. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  44. R. Liu et al. An intriguing failing of convolutional neural networks and the coordconv solution. Advances in Neural Information Processing Systems, 2018:9605–9616, 2018.
  45. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10561–10570, 2021.
  46. NTIRE 2024 quality assessment of AI-generated content challenge. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  47. NTIRE 2024 challenge on low light image enhancement: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  48. Vmamba: Visual state space model. arXiv preprint arXiv:2401.10166, 2024.
  49. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  50. Sgdr: Stochastic gradient descent with warm restarts. In ICLR, 2017.
  51. Image restoration with mean-reverting stochastic differential equations. arXiv preprint arXiv:2301.11699, 2023.
  52. Refusion: Enabling large-size realistic image restoration with latent-space diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1680–1691, 2023.
  53. Toward fast, flexible, and robust low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5637–5646, 2022.
  54. S G Mallat. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7):674–693, 1987.
  55. Zero-shot noise2noise: Efficient image denoising without any data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14018–14027, 2023.
  56. Edge detection in pipe images using classification of haar wavelet transforms. Applied Artificial Intelligence, 28(7):675–689, Aug. 2014.
  57. Making a “completely blind” image quality analyzer. IEEE Signal processing letters, 20(3):209–212, 2012.
  58. Light weight residual dense attention net for spectral reconstruction from rgb images. arXiv preprint arXiv:2004.06930, 2020.
  59. End-to-end depth-guided relighting using lightweight deep learning-based method. J. Imaging, 9:175, 2023.
  60. Motion estimation using low-band-shift method for wavelet-based moving-picture coding. IEEE Transactions on Image Processing, 9(4):577–587, Apr. 2000.
  61. Emanuel Parzen. On estimation of a probability density function and mode. The annals of mathematical statistics, 33(3):1065–1076, 1962.
  62. The ninth NTIRE 2024 efficient super-resolution challenge report. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  63. Chen Change Loy Shangchen Zhou, Chongyi Li. Lednet: Joint low-light enhancement and deblurring in the dark. In ECCV, 2022.
  64. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  65. NTIRE 2024 image shadow removal challenge report. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  66. NTIRE 2024 challenge on stereo image super-resolution: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  67. Ultra-high-definition low-light image enhancement: A benchmark and transformer-based method. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 2654–2662, 2023.
  68. NTIRE 2024 challenge on light field image super-resolution: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  69. Deep retinex decomposition for low-light enhancement. In British Machine Vison Conference, 2018.
  70. Snr-aware low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17714–17724, 2022.
  71. NTIRE 2024 challenge on blind enhancement of compressed image: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  72. Implicit neural representation for cooperative low-light image enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12918–12927, 2023.
  73. Towards efficient and scale-robust ultra-high-definition image demoiréing. In European Conference on Computer Vision, pages 646–662. Springer, 2022.
  74. A two-branch neural network for non-homogeneous dehazing via ensemble learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 193–202, 2021.
  75. NTIRE 2024 challenge on HR depth from images of specular and transparent surfaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  76. Learning enriched features for real image restoration and enhancement. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV 16, pages 492–511. Springer, 2020.
  77. Learning enriched features for fast image restoration and enhancement. IEEE transactions on pattern analysis and machine intelligence, 45(2):1934–1948, 2022.
  78. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018.
  79. NTIRE 2024 challenge on bracketing image restoration and enhancement: Datasets, methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
  80. Surroundnet: Towards effective low-light image enhancement. Pattern Recognition, 141:109602, 2023.
  81. Breaking through the haze: An advanced non-homogeneous dehazing method based on fast fourier convolution and convnext. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1894–1903, 2023.
  82. Zero-shot restoration of underexposed images via robust retinex decomposition. In 2020 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2020.
  83. Self-calibrated efficient transformer for lightweight super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 930–939, 2022.
Citations (19)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up