Real Image Deblurring Based on Implicit Degradation Representations and Reblur Estimation
Source abstract
Abstract
Most existing image deblurring methods are based on the estimation of blur kernels and end-to-end learning of the mapping relationship between blurred and sharp images. However, since different real-world blurred images typically have completely different blurring patterns, the performance of these methods in real image deblurring tasks is limited without explicitly modeling blurring as degradation representations. In this paper, we propose IDR2ENet, which is the Implicit Degradation Representations and Reblur Estimation Network, for real image deblurring. IDR2ENet consists of a degradation estimation process, a reblurring process, and a deblurring process. The degradation estimation process takes the real blurred image as input and outputs the implicit degradation representations estimated on it, which are used as the inputs of both reblurring and deblurring processes to better estimate the features of the blurred image. The experimental results show that whether compared with traditional or deep-learning-based deblurring algorithms, IDR2ENet achieves stable and efficient deblurring results on real blurred images.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image and Signal Denoising Methods · Image Processing Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China
China Mobile Communications Group Sichuan Co., Ltd., Chengdu 610094, China
Funding
National Natural Science Foundation of China · Key Research and Development Project of Sichuan Province
References (43)
Show source-provided references
1. Deep image deblurring: A survey10.1007/s11263-022-01633-5 ↗
2. Michaeli, T., and Irani, M. (2014, January 6–12). Blind deblurring using internal patch recurrence. Proceedings of the Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland. Proceedings, Part III 13.10.1007/978-3-319-10578-9_51 ↗
3. Krishnan, D., and Fergus, R. (2009, January 7–10). Fast image deconvolution using hyper-Laplacian priors. Proceedings of the 22nd International Conference on Neural Information Processing Systems (NIPS’ 09), Vancouver, BC, Canada.
4. Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., and Freeman, W.T. (2006). Acm Siggraph 2006 Papers, ACM.
5. Total variation blind deconvolution10.1109/83.661187 ↗
6. Xu, L., Zheng, S., and Jia, J. (2013, January 23–28). Unnatural l0 sparse representation for natural image deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.147 ↗
7. Fast Motion Deblurring10.1145/1618452.1618491 ↗
8. Nah, S., Hyun Kim, T., and Mu Lee, K. (2017, January 21–26). Deep multi-scale convolutional neural network for dynamic scene deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.35 ↗
9. Tao, X., Gao, H., Shen, X., Wang, J., and Jia, J. (2018, January 18–23). Scale-recurrent network for deep image deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00853 ↗
10. Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., and Matas, J. (2018, January 18–23). Deblurgan: Blind motion deblurring using conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00854 ↗
11. Schuler, C.J., Hirsch, M., Harmeling, S., and Schölkopf, B. (2014). Learning to Deblur. arXiv.
12. Xie, X., Jones, M.W., and Tam, G.K.L. (2015, January 7–10). Convolutional Neural Networks for Direct Text Deblurring. Proceedings of the British Machine Vision Conference (BMVC), Swansea, UK.
13. Ren, D., Zhang, K., Wang, Q., Hu, Q., and Zuo, W. (2020). Neural Blind Deconvolution Using Deep Priors. arXiv.10.1109/CVPR42600.2020.00340 ↗
14. Sun, J., Cao, W., Xu, Z., and Ponce, J. (2015). Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal. arXiv.10.1109/CVPR.2015.7298677 ↗
15. Chakrabarti, A. (2016). A Neural Approach to Blind Motion Deblurring. arXiv.10.1007/978-3-319-46487-9_14 ↗
16. Kupyn, O., Martyniuk, T., Wu, J., and Wang, Z. (November, January 27). Deblurgan-v2: Deblurring (orders-of-magnitude) faster and better. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
17. Nimisha, T.M., Kumar Singh, A., and Rajagopalan, A.N. (2017, January 22–29). Blur-invariant deep learning for blind-deblurring. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.509 ↗
18. Lu, B., Chen, J.C., and Chellappa, R. (2019). Unsupervised Domain-Specific Deblurring via Disentangled Representations. arXiv.10.1109/CVPR.2019.01047 ↗
19. Gao, H., Tao, X., Shen, X., and Jia, J. (2019, January 15–20). Dynamic scene deblurring with parameter selective sharing and nested skip connections. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00397 ↗
20. Shen, Z., Lai, W.S., Xu, T., Kautz, J., and Yang, M.H. (2018, January 18–23). Deep semantic face deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00862 ↗
21. Hu, Z., Cho, S., Wang, J., and Yang, M.H. (2014, January 23–28). Deblurring low-light images with light streaks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.432 ↗
22. Jolicoeur-Martineau, A. (2018). The relativistic discriminator: A key element missing from standard GAN. arXiv.
23. Denoising prior driven deep neural network for image restoration10.1109/TPAMI.2018.2873610 ↗
24. An effective deep network using target vector update modules for image restoration10.1016/j.patcog.2021.108333 ↗
25. Qin, M., Ren, C., Yang, H., He, X., and Wang, Z. (2023). Blind Image Denoising via Deep Unfolding Network with Degradation Information Guidance. IEEE Trans. Circuits Syst. II Express Briefs.10.1109/TCSII.2023.3249297 ↗
26. Li, D., Zhang, Y., Cheung, K.C., Wang, X., Qin, H., and Li, H. (2022, January 23–27). Learning Degradation Representations for Image Deblurring. Proceedings of the Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel. Proceedings, Part XVIII.10.1007/978-3-031-19797-0_42 ↗
27. Blind deconvolution of spatially invariant image blurs with phase10.1109/TASSP.1976.1162770 ↗
28. Blind image deconvolution10.1109/79.489268 ↗
29. Xu, L., and Jia, J. (2010, January 5–11). Two-phase kernel estimation for robust motion deblurring. Proceedings of the Computer Vision–ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Greece. Proceedings, Part I 11.10.1007/978-3-642-15549-9_12 ↗
30. Bahat, Y., Efrat, N., and Irani, M. (2017, January 22–29). Non-uniform blind deblurring by reblurring. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.356 ↗
31. Zhang, K., Luo, W., Zhong, Y., Ma, L., Stenger, B., Liu, W., and Li, H. (2020, January 13–19). Deblurring by realistic blurring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00281 ↗
32. Chen, H., Gu, J., Gallo, O., Liu, M.Y., Veeraraghavan, A., and Kautz, J. (2018, January 4–6). Reblur2deblur: Deblurring videos via self-supervised learning. Proceedings of the 2018 IEEE International Conference on Computational Photography (ICCP), Pittsburgh, PA, USA.10.1109/ICCPHOT.2018.8368468 ↗
33. Wang, L., Wang, Y., Dong, X., Xu, Q., Yang, J., An, W., and Guo, Y. (2021, January 20–25). Unsupervised degradation representation learning for blind super-resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01044 ↗
34. Johnson, J., Alahi, A., and Fei-Fei, L. (2016, January 11–14). Perceptual losses for real-time style transfer and super-resolution. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part II 14.10.1007/978-3-319-46475-6_43 ↗
35. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
36. Wang, Z., Simoncelli, E.P., and Bovik, A.C. (2003, January 9–12). Multiscale structural similarity for image quality assessment. Proceedings of the IEEE Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, USA.
37. Rim, J., Lee, H., Won, J., and Cho, S. (2020, January 23–28). Real-world blur dataset for learning and benchmarking deblurring algorithms. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XXV 16.10.1007/978-3-030-58595-2_12 ↗
38. Pan, J., Sun, D., Pfister, H., and Yang, M.H. (2016, January 27–30). Blind image deblurring using dark channel prior. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.180 ↗
39. Zhang, J., Pan, J., Ren, J., Song, Y., Bao, L., Lau, R.W., and Yang, M.H. (2018, January 18–23). Dynamic scene deblurring using spatially variant recurrent neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00267 ↗
40. Zhang, H., Dai, Y., Li, H., and Koniusz, P. (2019, January 15–20). Deep stacked hierarchical multi-patch network for image deblurring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00613 ↗
41. Cho, S.J., Ji, S.W., Hong, J.P., Jung, S.W., and Ko, S.J. (2021, January 11–17). Rethinking coarse-to-fine approach in single image deblurring. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00460 ↗
42. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2021, January 20–25). Multi-stage progressive image restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01458 ↗
43. Lightweight MIMO-WNet for single image deblurring10.1016/j.neucom.2022.10.028 ↗