Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring (2401.00027v2)

Published 29 Dec 2023 in cs.CV

Abstract: Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however, in the context of deep learning, existing multi-scale algorithms not only require the use of complex modules for feature fusion of low-scale RGB images and deep semantics, but also manually generate low-resolution pairs of images that do not have sufficient confidence. In this work, we propose a multi-scale network based on single-input and multiple-outputs(SIMO) for motion deblurring. This simplifies the complexity of algorithms based on a coarse-to-fine scheme. To alleviate restoration defects impacting detail information brought about by using a multi-scale architecture, we combine the characteristics of real-world blurring trajectories with a learnable wavelet transform module to focus on the directional continuity and frequency features of the step-by-step transitions between blurred images to sharp images. In conclusion, we propose a multi-scale network with a learnable discrete wavelet transform (MLWNet), which exhibits state-of-the-art performance on multiple real-world deblurred datasets, in terms of both subjective and objective quality as well as computational efficiency.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. An efficient statistical method for image noise level estimation. In Proceedings of the IEEE International Conference on Computer Vision, pages 477–485, 2015.
  2. Simple baselines for image restoration. In European Conference on Computer Vision, pages 17–33. Springer, 2022.
  3. Rethinking coarse-to-fine approach in single image deblurring. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4641–4650, 2021.
  4. Selective frequency network for image restoration. In International Conference on Learning Representations, ICLR, 2023.
  5. Ingrid Daubechies. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory, 36(5):961–1005, 1990.
  6. Nas-fpn: Learning scalable feature pyramid architecture for object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7036–7045, 2019.
  7. Adaptive wavelet distillation from neural networks through interpretations. Advances in Neural Information Processing Systems, 34:20669–20682, 2021.
  8. Mstr: Multi-scale transformer for end-to-end human-object interaction detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19578–19587, 2022a.
  9. Mssnet: Multi-scale-stage network for single image deblurring. In European Conference on Computer Vision, pages 524–539. Springer, 2022b.
  10. Efficient frequency domain-based transformers for high-quality image deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5886–5895, 2023.
  11. Deblurgan: Blind motion deblurring using conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8183–8192, 2018.
  12. Deblurgan-v2: Deblurring (orders-of-magnitude) faster and better. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8878–8887, 2019.
  13. Learning degradation representations for image deblurring. In European Conference on Computer Vision, pages 736–753. Springer, 2022.
  14. Efficient and explicit modelling of image hierarchies for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18278–18289, 2023.
  15. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017.
  16. Multi-level wavelet convolutional neural networks. IEEE Access, 7:74973–74985, 2019.
  17. Path aggregation network for instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8759–8768, 2018.
  18. Densely self-guided wavelet network for image denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 432–433, 2020.
  19. Deep residual fourier transformation for single image deblurring. arxiv 2021. arXiv preprint arXiv:2111.11745, 2021.
  20. 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.
  21. Multi-temporal recurrent neural networks for progressive non-uniform single image deblurring with incremental temporal training. In European Conference on Computer Vision, pages 327–343. Springer, 2020.
  22. Fcanet: Frequency channel attention networks. In Proceedings of the IEEE/CVF international conference on computer vision, pages 783–792, 2021.
  23. Real-world blur dataset for learning and benchmarking deblurring algorithms. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV 16, pages 184–201. Springer, 2020.
  24. Realistic blur synthesis for learning image deblurring. In European conference on computer vision, pages 487–503. Springer, 2022.
  25. Resolution-robust large mask inpainting with fourier convolutions. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 2149–2159, 2022.
  26. Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10781–10790, 2020.
  27. Scale-recurrent network for deep image deblurring. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8174–8182, 2018.
  28. Stripformer: Strip transformer for fast image deblurring. In European Conference on Computer Vision, pages 146–162. Springer, 2022a.
  29. Banet: a blur-aware attention network for dynamic scene deblurring. IEEE Transactions on Image Processing, 31:6789–6799, 2022b.
  30. Maxim: Multi-axis mlp for image processing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5769–5780, 2022.
  31. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7464–7475, 2023.
  32. Image classification using convolutional neural network with wavelet domain inputs. IET Image Processing, 16(8):2037–2048, 2022.
  33. Uformer: A general u-shaped transformer for image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17683–17693, 2022.
  34. Adaptive wavelet pooling for convolutional neural networks. In International Conference on Artificial Intelligence and Statistics, pages 1936–1944. PMLR, 2021.
  35. Fda: Fourier domain adaptation for semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4085–4095, 2020.
  36. Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. International Journal of Computer Vision, 129:3051–3068, 2021.
  37. Multi-stage progressive image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14821–14831, 2021.
  38. Restormer: Efficient transformer for high-resolution image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5728–5739, 2022.
  39. Deep stacked hierarchical multi-patch network for image deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5978–5986, 2019.
  40. Deblurring by realistic blurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2737–2746, 2020.
  41. Detecting camouflaged object in frequency domain. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4504–4513, 2022.
  42. Sdwnet: A straight dilated network with wavelet transformation for image deblurring. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1895–1904, 2021.
Citations (4)
View on Semantic Scholar

Summary

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

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