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

Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (2403.12933v1)

Published 19 Mar 2024 in cs.CV

Abstract: Understanding illumination and reducing the need for supervision pose a significant challenge in low-light enhancement. Current approaches are highly sensitive to data usage during training and illumination-specific hyper-parameters, limiting their ability to handle unseen scenarios. In this paper, we propose a new zero-reference low-light enhancement framework trainable solely with normal light images. To accomplish this, we devise an illumination-invariant prior inspired by the theory of physical light transfer. This prior serves as the bridge between normal and low-light images. Then, we develop a prior-to-image framework trained without low-light data. During testing, this framework is able to restore our illumination-invariant prior back to images, automatically achieving low-light enhancement. Within this framework, we leverage a pretrained generative diffusion model for model ability, introduce a bypass decoder to handle detail distortion, as well as offer a lightweight version for practicality. Extensive experiments demonstrate our framework's superiority in various scenarios as well as good interpretability, robustness, and efficiency. Code is available on our project homepage: http://daooshee.github.io/QuadPrior-Website/

Definition Search Book Streamline Icon: https://streamlinehq.com
References (67)
  1. Improving image generation with better captions. 2023.
  2. Learning photographic global tonal adjustment with a database of input / output image pairs. In CVPR, 2011.
  3. Retinexformer: One-stage retinex-based transformer for low-light image enhancement. In ICCV, 2023.
  4. Learning to see in the dark. In CVPR, 2018.
  5. Seeing motion in the dark. In ICCV, 2019.
  6. An efficient statistical method for image noise level estimation. In ICCV, 2015.
  7. Learning a simple low-light image enhancer from paired low-light instances. In CVPR, 2023.
  8. Color invariance. IEEE TPAMI, 23(12):1338–1350, 2001.
  9. Color in computer vision: Fundamentals and applications. John Wiley & Sons, 2012.
  10. Zero-reference deep curve estimation for low-light image enhancement. In CVPR, 2020.
  11. LIME: Low-light image enhancement via illumination map estimation. IEEE TIP, 26(2):982–993, 2017.
  12. R2RNet: Low-light image enhancement via real-low to real-normal network. Journal of Visual Communication and Image Representation, 90:103712, 2023.
  13. Learning profitable NFT image diffusions via multiple visual-policy guided reinforcement learning. In ACM MM, 2023.
  14. Denoising diffusion probabilistic models. In NeurIPS, 2020.
  15. Towards low light enhancement with RAW images. IEEE TIP, 31:1391–1405, 2022a.
  16. Deep fourier-based exposure correction network with spatial-frequency interaction. In ECCV, 2022b.
  17. Learning to see moving objects in the dark. In ICCV, 2019.
  18. Low-light image enhancement with wavelet-based diffusion models. In Siggraph Asia, 2023.
  19. EnlightenGAN: Deep light enhancement without paired supervision. IEEE TIP, 30:2340–2349, 2021.
  20. Adam: A method for stochastic optimization. arXiv, 2014.
  21. Contrast enhancement based on layered difference representation of 2D histograms. IEEE TIP, 22(12):5372–5384, 2013.
  22. Zero-shot domain adaptation with a physics prior. In ICCV, 2021.
  23. Learning to enhance low-light image via zero-reference deep curve estimation. IEEE TPAMI, 44(8):4225–4238, 2021.
  24. Cudi: Curve distillation for efficient and controllable exposure adjustment. arXiv, 2022.
  25. Flexicurve: Flexible piecewise curves estimation for photo retouching. In CVPRW, 2023.
  26. Structure-revealing low-light image enhancement via robust retinex model. IEEE TIP, 27(6):2828–2841, 2018.
  27. Iterative prompt learning for unsupervised backlit image enhancement. In ICCV, 2023.
  28. Microsoft COCO: Common objects in context. In ECCV, 2014.
  29. Learning trajectory-aware transformer for video super-resolution. In CVPR, 2022.
  30. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In CVPR, 2021.
  31. Llnet: A deep autoencoder approach to natural low-light image enhancement. PR, 61:650–662, 2017.
  32. Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models. arXiv, 2022.
  33. Perceptual quality assessment for multi-exposure image fusion. IEEE TIP, 24(11):3345–3356, 2015.
  34. Toward fast, flexible, and robust low-light image enhancement. In CVPR, 2022a.
  35. AI illustrator: Translating raw descriptions into images by prompt-based cross-modal generation. In ACM MM, 2022b.
  36. No-reference image quality assessment in the spatial domain. IEEE TIP, 21(12):4695–4708, 2012.
  37. Contrast-limited adaptive histogram equalization: Speed and effectiveness. In VBC, 1990.
  38. Learning spatiotemporal frequency-transformer for compressed video super-resolution. In ECCV, 2022.
  39. Learning degradation-robust spatiotemporal frequency-transformer for video super-resolution. IEEE TPAMI, 45(12):14888–14904, 2023.
  40. Retinex processing for automatic image enhancement. Journal of Electronic Imaging, 2004.
  41. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In KDD, 2020.
  42. High-resolution image synthesis with latent diffusion models. In CVPR, 2022.
  43. Mm-diffusion: Learning multi-modal diffusion models for joint audio and video generation. In CVPR, 2023.
  44. Image super-resolution via iterative refinement. IEEE TPAMI, 45(4):4713–4726, 2023.
  45. On the evaluation of illumination compensation algorithms. Multimedia Tools and Applications, 77:9211–9231, 2018.
  46. Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE TIP, 22(9):3538–3548, 2013.
  47. Low-light image enhancement with normalizing flow. In AAAI, 2022.
  48. Deep retinex decomposition for low-light enhancement. In BMVC, 2018.
  49. Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. In CVPR, 2022.
  50. Learning semantic-aware knowledge guidance for low-light image enhancement. In CVPR, 2023.
  51. Deep denoising of flash and no-flash pairs for photography in low-light environments. In CVPR, 2021.
  52. Seeing in extra darkness using a deep-red flash. In CVPR, 2021.
  53. Learning texture transformer network for image super-resolution. In CVPR, 2020a.
  54. Implicit neural representation for cooperative low-light image enhancement. In ICCV, 2023.
  55. From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement. In CVPR, 2020b.
  56. Advancing image understanding in poor visibility environments: A collective benchmark study. IEEE TIP, 29:5737–5752, 2020c.
  57. Diff-retinex: Rethinking low-light image enhancement with A generative diffusion model. In ICCV, 2023.
  58. Restormer: Efficient transformer for high-resolution image restoration. In CVPR, 2022.
  59. Learning temporal consistency for low light video enhancement from single images. In CVPR, 2021a.
  60. Adding conditional control to text-to-image diffusion models. In ICCV, 2023.
  61. Zero-shot restoration of back-lit images using deep internal learning. In ACM MM, 2019a.
  62. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, 2018.
  63. Kindling the darkness: A practical low-light image enhancer. In ACM MM, 2019b.
  64. Beyond brightening low-light images. IJCV, 129(4):1013–1037, 2021b.
  65. Pyramid diffusion models for low-light image enhancement. In IJCAI, 2023.
  66. Moviefactory: Automatic movie creation from text using large generative models for language and images. In ACM MM, 2023a.
  67. Mobilevidfactory: Automatic diffusion-based social media video generation for mobile devices from text. In ACM MM, 2023b.
Citations (9)
View on Semantic Scholar

Summary

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

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