Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 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

MCMS: Multi-Category Information and Multi-Scale Stripe Attention for Blind Motion Deblurring (2405.01083v1)

Published 2 May 2024 in cs.CV

Abstract: Deep learning-based motion deblurring techniques have advanced significantly in recent years. This class of techniques, however, does not carefully examine the inherent flaws in blurry images. For instance, low edge and structural information are traits of blurry images. The high-frequency component of blurry images is edge information, and the low-frequency component is structure information. A blind motion deblurring network (MCMS) based on multi-category information and multi-scale stripe attention mechanism is proposed. Given the respective characteristics of the high-frequency and low-frequency components, a three-stage encoder-decoder model is designed. Specifically, the first stage focuses on extracting the features of the high-frequency component, the second stage concentrates on extracting the features of the low-frequency component, and the third stage integrates the extracted low-frequency component features, the extracted high-frequency component features, and the original blurred image in order to recover the final clear image. As a result, the model effectively improves motion deblurring by fusing the edge information of the high-frequency component and the structural information of the low-frequency component. In addition, a grouped feature fusion technique is developed so as to achieve richer, more three-dimensional and comprehensive utilization of various types of features at a deep level. Next, a multi-scale stripe attention mechanism (MSSA) is designed, which effectively combines the anisotropy and multi-scale information of the image, a move that significantly enhances the capability of the deep model in feature representation. Large-scale comparative studies on various datasets show that the strategy in this paper works better than the recently published measures.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. P. Yu, F. Zhou, X. Zhang, X. Qiu, M. Kadoch, and M. Cheriet, “Deep learning-based resource allocation for 5G broadband TV service,” IEEE Trans. Broadcast., vol. 66, no. 4, pp. 800–813, 2020.
  2. J. Pan, D. Sun, H. Pfister, and M. Yang, “Deblurring images via dark channel prior,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 10, pp. 2315–2328, 2018.
  3. L. Xu, S. Zheng, and J. Jia, “Unnatural L0 sparse representation for natural image deblurring,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2013, pp. 1107–1114.
  4. Y. Yan, W. Ren, Y. Guo, R. Wang, and X. Cao, “Image deblurring via extreme channels prior,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 6978–6986.
  5. L. Chen, F. Fang, T. Wang, and G. Zhang, “Blind image deblurring with local maximum gradient prior,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 1742–1750.
  6. J. Pan, Z. Hu, Z. Su, and M. Yang, “Deblurring text images via L0-regularized intensity and gradient prior,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2014, pp. 2901–2908.
  7. J. Dong, J. Pan, Z. Su, and M. Yang, “Blind image deblurring with outlier handling,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 2478–2486.
  8. Y. Bahat, N. Efrat, and M. Irani, “Non-uniform blind deblurring by reblurring,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 3286–3294.
  9. B. Sheng, P. Li, X. Fang, P. Tan, and E. Wu, “Depth-aware motion deblurring using loopy belief propagation,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 4, pp. 955–969, 2019.
  10. H. Ullah, K. Muhammad, M. Irfan, S. Anwar, M. Sajjad, A. S. Imran, and V. H. C. D. Albuquerque, “Light-DehazeNet: a novel lightweight CNN architecture for single image dehazing,” IEEE Trans. Image Process., vol. 30, pp. 8968–8982, 2021.
  11. W. Song, Y. Wang, D. Huang, A. Liotta, and C. Perra, “Enhancement of underwater images with statistical model of background light and optimization of transmission map,” IEEE Trans. Broadcast., vol. 66, no. 1, pp. 153–169, 2020.
  12. A. Esmaeilzehi, M. O. Ahmad, M. N. and S. Swamy, “SRNMSM: A deep light-weight image super resolution network using multi-scale spatial and morphological feature generating residual blocks,” IEEE Trans. Broadcast., vol. 68, no. 1, pp. 58–68, 2021.
  13. J. Wan, H. Yin, Z. Liu Z, A. Chong, and Y. Liu, “Lightweight image super-resolution by multi-scale aggregation,” IEEE Trans. Broadcast., vol. 67, no. 2, pp. 372–382, 2020.
  14. A. Chakrabarti, “A neural approach to blind motion deblurring,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 221–235.
  15. S. Nah, T. H. Kim, and K. M. Lee, “Deep multi-scale convolutional neural network for dynamic scene deblurring,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 3883–3891.
  16. X. Tao, H. Gao, X. Shen, J. Wang, and J. Jia, “Scale-recurrent network for deep image deblurring,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 8174–8182.
  17. H. Gao, X. Tao, X. Shen, and J. Jia, “Dynamic scene deblurring with parameter selective sharing and nested skip connections,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 3848–3856.
  18. H. Zhang, Y. Dai, H. Li, and P. Koniusz, “Deep stacked hierarchical multi-patch network for image deblurring,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 5978–5986.
  19. D. Park, D. U. Kang, J. Kim, S. Y. Chun, “Multi-temporal recurrent neural networks for progressive non-uniform single image deblurring with incremental temporal training,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 327–343.
  20. S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M. H. Yang, and L. Shao, “Multi-stage progressive image restoration,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 14821–14831.
  21. A. Esmaeilzehi, M. O. Ahmad, and M. N. S. Swamy, “UPDResNN: A deep light-weight image upsampling and deblurring residual neural network,” IEEE Trans. Broadcast., vol. 67, no. 2, pp. 538–548, 2021.
  22. S. W. Ji, J. Lee, S. W. Kim, J. P. Hong, S. J. Baek, S. W. Jung, and S. J. Ko, “XYDeblur: Divide and Conquer for Single Image Deblurring,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 17421–17430.
  23. Y. Liu, F. Fang, T. Wang, J. Li, Y. Sheng, and G. Zhang, “Multi-scale grid network for image deblurring with high-frequency guidance,” IEEE Trans. Multimedia., vol. 24, pp. 2890–2901, 2021.
  24. B. Luo, Z. Cheng, L. Xu, G. Zhang, and H. Li, “Blind image deblurring via superpixel segmentation prior,” IEEE Trans. Circuits Syst. Video Technol., vol. 32, no. 3, pp. 1467–1482, 2021.
  25. K. R. Rao, and P.Yip, “Discrete cosine transform - algorithms, advantages, applications,” Elsevier Science and Technology Books, 1st, Aug. 1990. [Online]. Available: https://books.google.com.hk/books?id=dSoaogEACAAJ.
  26. M. Farge, “Wavelet transforms and their applications to turbulence,” in (ARFM), 1992, pp. 395–457.
  27. P. V. Hough, “Method and means for recognizing complex patterns,” Dec. 1962. [Online]. Available: https://www.osti.gov/biblio/4746348.
  28. E. H. Land, and J. McCann, “Lightness and retinex theory,” J. Opt. Soc. Amer., vol. 61, no. 1, pp. 1–11, 1971.
  29. J. Zhang, C. Zhang, J. Wang J, Q.Xiong, Y. Zhang, and W. zhang, “Attention driven self-similarity capture for motion deblurring,” in (ICME), 2021, pp. 1–6.
  30. S. J. Cho, S. W. Ji, J. P. Hong, S. W. Jung, and S. J. Ko, “Rethinking coarse-to-fine approach in single image deblurring,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2021, pp. 4641–4650.
  31. C. Liu, W. Ke, F. Qin, and Q. Ye, “Linear span network for object skeleton detection,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 133–148.
  32. C. Liu, Y. Tian, Z. Chen, J. Jiao, and Q. Ye, “Adaptive linear span network for object skeleton detection,” IEEE Trans. Image Process., vol. 30, pp. 5096–5108, 2021.
  33. J. Rim, H. Lee, J. Won, and S. Cho, “Real-world blur dataset for learning and benchmarking deblurring algorithms,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2020, pp. 184–201.
  34. Y. Liu, B. Lu, J. Peng, and Z. Zhang, “Research on the use of YOLOv5 object detection algorithm in mask wearing recognition,” World Sci. Res. J., vol. 6, no. 11, pp. 276–284, 2020.
  35. S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, and M. H. Yang, “Restormer: Efficient transformer for high-resolution image restoration,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 5728–5739.
  36. Land E H, McCann J J, “Lightness and retinex theory,” Journal of the Optical Society of America, vol. 61, no. 1, pp. 1–11, 1971.
  37. Zhang J, Zhang C, Wang J, et al, “Attention driven self-similarity capture for motion deblurring,” in 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1–6.
  38. Li Y, Fan Y, Xiang X, et al, “Efficient and explicit modelling of image hierarchies for image restoration,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2023, pp. 18278–18289.
  39. Zhang K, Luo W, Zhong Y, et al, “Deblurring by realistic blurring,” in Proc. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 184–201.
  40. Chen L, Chu X, Zhang X, et al, “Simple baselines for image restoration,” in European Conference on Computer Vision (ECCV), 2022, pp. 17–33.
  41. Zhang Y, Li Q, Qi M, et al, “Multi-scale frequency separation network for image deblurring,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 10, pp. 5525–5537, 2023.

Summary

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

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

Tweets