Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
GPT-5.1
GPT-5.1 96 tok/s
Gemini 3.0 Pro 48 tok/s Pro
Gemini 2.5 Flash 155 tok/s Pro
Kimi K2 197 tok/s Pro
Claude Sonnet 4.5 36 tok/s Pro
2000 character limit reached

CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task (2404.14132v1)

Published 22 Apr 2024 in cs.CV and eess.IV

Abstract: In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. Ntire 2020 challenge on real image denoising: Dataset, methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 496–497, 2020.
  2. Burst image deblurring using permutation invariant convolutional neural networks. In The European Conference on Computer Vision (ECCV), 2018.
  3. Deep reparametrization of multi-frame super-resolution and denoising, 2021.
  4. Luca Bogoni. Extending dynamic range of monochrome and color images through fusion. In Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, pages 7–12. IEEE, 2000.
  5. Unprocessing images for learned raw denoising. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11036–11045, 2019.
  6. Low-light image restoration with short-and long-exposure raw pairs. IEEE Transactions on Multimedia, 24:702–714, 2021.
  7. Rethinking coarse-to-fine approach in single image deblurring. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4641–4650, 2021.
  8. Scaling up your kernels to 31x31: Revisiting large kernel design in cnns. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11963–11975, 2022.
  9. Hdr image reconstruction from a single exposure using deep cnns. ACM transactions on graphics (TOG), 36(6):1–15, 2017.
  10. Creating cinematic wide gamut hdr-video for the evaluation of tone mapping operators and hdr-displays. In Digital photography X, pages 279–288. SPIE, 2014.
  11. Deep burst denoising, 2017.
  12. Thorsten Grosch et al. Fast and robust high dynamic range image generation with camera and object movement. Vision, Modeling and Visualization, RWTH Aachen, 277284(3):2, 2006.
  13. Toward convolutional blind denoising of real photographs. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1712–1722, 2019.
  14. Hdr deghosting: How to deal with saturation? In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1163–1170, 2013.
  15. Generating content for hdr deghosting from frequency view. arXiv preprint arXiv:2404.00849, 2024.
  16. Deep high dynamic range imaging of dynamic scenes. ACM Trans. Graph., 36(4):144–1, 2017.
  17. High dynamic range video. ACM Transactions on Graphics (TOG), 22(3):319–325, 2003.
  18. Joint demosaicing and deghosting of time-varying exposures for single-shot hdr imaging. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12292–12301, 2023.
  19. Face deblurring using dual camera fusion on mobile phones. ACM Transactions on Graphics (TOG), 41(4):1–16, 2022.
  20. High dynamic range and super-resolution from raw image bursts. arXiv preprint arXiv:2207.14671, 2022.
  21. Uphdr-gan: Generative adversarial network for high dynamic range imaging with unpaired data. IEEE Transactions on Circuits and Systems for Video Technology, 32(11):7532–7546, 2022.
  22. Ntire 2023 challenge on image denoising: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1904–1920, 2023.
  23. A convnet for the 2020s. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11976–11986, 2022a.
  24. Ghost-free high dynamic range imaging with context-aware transformer. In European Conference on Computer Vision, pages 344–360. Springer, 2022b.
  25. Transformer for single image super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 457–466, 2022.
  26. An iterative image registration technique with an application to stereo vision. In IJCAI’81: 7th international joint conference on Artificial intelligence, pages 674–679, 1981.
  27. Robust multi-exposure image fusion: a structural patch decomposition approach. IEEE Transactions on Image Processing, 26(5):2519–2532, 2017.
  28. Intriguing findings of frequency selection for image deblurring. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1905–1913, 2023.
  29. Gated multi-resolution transfer network for burst restoration and enhancement. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22201–22210. IEEE, 2023.
  30. Burst denoising with kernel prediction networks, 2018.
  31. Deep multi-scale convolutional neural network for dynamic scene deblurring. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3883–3891, 2017.
  32. Hdr-gan: Hdr image reconstruction from multi-exposed ldr images with large motions. IEEE Transactions on Image Processing, 30:3885–3896, 2021.
  33. Bitmap movement detection: Hdr for dynamic scenes. In 2010 Conference on Visual Media Production, pages 1–8. IEEE, 2010.
  34. A fast, scalable, and reliable deghosting method for extreme exposure fusion. In 2019 IEEE International Conference on Computational Photography (ICCP), pages 1–8. IEEE, 2019.
  35. Towards practical and efficient high-resolution hdr deghosting with cnn. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXI 16, pages 497–513. Springer, 2020.
  36. Optical flow estimation using a spatial pyramid network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4161–4170, 2017.
  37. Robust patch-based hdr reconstruction of dynamic scenes. ACM Trans. Graph., 31(6):203–1, 2012.
  38. Dual-camera joint deblurring-denoising. arXiv preprint arXiv:2309.08826, 2023.
  39. Selective transhdr: Transformer-based selective hdr imaging using ghost region mask. In European Conference on Computer Vision, pages 288–304. Springer, 2022.
  40. Scale-recurrent network for deep image deblurring. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8174–8182, 2018.
  41. Alignment-free hdr deghosting with semantics consistent transformer. arXiv preprint arXiv:2305.18135, 2023.
  42. Multi-depth branch network for efficient image super-resolution. Image and Vision Computing, page 104949, 2024.
  43. Image registration for multi-exposure high dynamic range image acquisition. 2007.
  44. Towards real-world burst image super-resolution: Benchmark and method. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13233–13242, 2023.
  45. Unpaired learning of deep image denoising. In European conference on computer vision, pages 352–368. Springer, 2020.
  46. Attention-guided network for ghost-free high dynamic range imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1751–1760, 2019.
  47. Deep hdr imaging via a non-local network. IEEE Transactions on Image Processing, 29:4308–4322, 2020.
  48. Dual-attention-guided network for ghost-free high dynamic range imaging. International Journal of Computer Vision, pages 1–19, 2022.
  49. A unified hdr imaging method with pixel and patch level. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22211–22220, 2023a.
  50. Towards high-quality hdr deghosting with conditional diffusion models. IEEE Transactions on Circuits and Systems for Video Technology, 2023b.
  51. Smae: Few-shot learning for hdr deghosting with saturation-aware masked autoencoders. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5775–5784, 2023c.
  52. Image deblurring with blurred/noisy image pairs. In ACM SIGGRAPH 2007 papers, pages 1–es. 2007.
  53. Cycleisp: Real image restoration via improved data synthesis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2696–2705, 2020.
  54. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE transactions on image processing, 26(7):3142–3155, 2017.
  55. Gradient-directed multiexposure composition. IEEE Transactions on Image Processing, 21(4):2318–2323, 2011.
  56. Self-supervised image restoration with blurry and noisy pairs. Advances in Neural Information Processing Systems, 35:29179–29191, 2022.
  57. Bracketing is all you need: Unifying image restoration and enhancement tasks with multi-exposure images. arXiv preprint arXiv:2401.00766, 2024a.
  58. 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, 2024b.
  59. Ligeng Zhu. Thop: Pytorch-opcounter, 2022. https://pypi.org/project/thop.

Summary

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

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

Open Problems

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

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

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up