ABSTRACT
Camera shake and object movement are the two prime causes of blurred images. Efficient feature extraction is crucial for deblurring. Although the existing methods have achieved remarkable achievements in the deblurring task, there is still room for improvement in effects. In this paper, we propose an efficient architecture called the feature catcher network(FCN). In this multi-stage FCN architecture, the following design allows us to achieve improvements in performance. Firstly, we propose to apply different calculated trust ratios to the output results of different stages before calculating losses and then carry out the cumulative evaluation to update parameters for backpropagation. Secondly, we have improved Transformer to create a query-key mechanism that is effect-friendly to the deblurring task. Thirdly, we propose a multi-stage attention block to make up for the loss of information in high-level feature extraction. And the enhanced feature extraction block is employed to capture detailed information to ensure a greater degree of image recovery. Fourthly, besides considering detailed features and high-level features at the same stage, we also construct residual supplements for blurry images in the raw information mechanism. The experimental results on several datasets demonstrate that our model(FCN) outperforms state-of-the-art methods in terms of deblurring effect. The code and models will be available at https://github.com/XinyueZhangqdu/FCN.
- Yuzhu Ji, Haijun Zhang, Zhao Zhang, and Ming Liu. 2021. CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances. Information Sciences 546(2021), 835–857.Google ScholarCross Ref
- Günter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. 2017. Self-normalizing neural networks. Advances in neural information processing systems 30 (2017).Google Scholar
- Donghyeon Lee, Chulhee Lee, and Taesung Kim. 2021. Wide receptive field and channel attention network for jpeg compressed image deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 304–313.Google ScholarCross Ref
- Ru Li, Junwei Xie, Yuyang Xue, Wenbin Zou, Tong Tong, Ming Luo, and Qinquan Gao. 2022. Enhanced multi-stage network for defocus deblurring using dual-pixel images. In Thirteenth International Conference on Signal Processing Systems (ICSPS 2021), Vol. 12171. SPIE, 162–168.Google ScholarCross Ref
- Jinping Liu, Quanquan Gao, Zhaohui Tang, Yongfang Xie, Weihua Gui, Tianyu Ma, and Jean Paul Niyoyita. 2020. Online monitoring of flotation froth bubble-size distributions via multiscale deblurring and multistage jumping feature-fused full convolutional networks. IEEE Transactions on Instrumentation and Measurement 69, 12(2020), 9618–9633. https://doi.org/10.1109/TIM.2020.3006629Google ScholarCross Ref
- Lu Lu, Yeonjong Shin, Yanhui Su, and George Em Karniadakis. 2019. Dying relu and initialization: Theory and numerical examples. arXiv preprint arXiv:1903.06733(2019).Google Scholar
- Haoyu Ma, Shaojun Liu, Qingmin Liao, Juncheng Zhang, and Jing-Hao Xue. 2021. Defocus Image Deblurring Network With Defocus Map Estimation as Auxiliary Task. IEEE Transactions on Image Processing 31 (2021), 216–226.Google ScholarDigital Library
- Seungjun Nah, Tae Hyun Kim, and Kyoung Mu Lee. 2017. Deep multi-scale convolutional neural network for dynamic scene deblurring. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3883–3891.Google ScholarCross Ref
- Dongwon Park, Dong Un Kang, Jisoo Kim, and Se Young Chun. 2020. Multi-temporal recurrent neural networks for progressive non-uniform single image deblurring with incremental temporal training. In European Conference on Computer Vision. Springer, 327–343. https://doi.org/10.1007/978-3-030-58539-6_20Google ScholarDigital Library
- Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, and Aleksander Madry. 2018. How does batch normalization help optimization?Advances in neural information processing systems 31 (2018).Google Scholar
- Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbing Shen, Haibin Ling, Tingfa Xu, and Ling Shao. 2019. Human-aware motion deblurring. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5572–5581. https://doi.org/10.1109/ICCV.2019.00567Google ScholarCross Ref
- Maitreya Suin, Kuldeep Purohit, and AN Rajagopalan. 2020. Spatially-attentive patch-hierarchical network for adaptive motion deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3606–3615. https://doi.org/10.1109/CVPR42600.2020.00366Google ScholarCross Ref
- Zhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou, Jianzhuang Liu, and Houqiang Li. 2022. Uformer: A general u-shaped transformer for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 17683–17693.Google ScholarCross Ref
- Jay Whang, Mauricio Delbracio, Hossein Talebi, Chitwan Saharia, Alexandros G Dimakis, and Peyman Milanfar. 2022. Deblurring via stochastic refinement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16293–16303.Google ScholarCross Ref
- Si Xi, Jia Wei, and Weidong Zhang. 2021. Pixel-guided dual-branch attention network for joint image deblurring and super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 532–540.Google ScholarCross Ref
- Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. 2022. Restormer: Efficient transformer for high-resolution image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5728–5739.Google ScholarCross Ref
- Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, and Ling Shao. 2021. Multi-stage progressive image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14821–14831. https://doi.org/10.48550/arXiv.2102.02808Google ScholarCross Ref
- Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, and Ling Shao. 2021. Multi-stage progressive image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14821–14831. https://doi.org/10.48550/arXiv.2102.02808Google ScholarCross Ref
- Hongguang Zhang, Yuchao Dai, Hongdong Li, and Piotr Koniusz. 2019. Deep stacked hierarchical multi-patch network for image deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5978–5986. https://doi.org/10.1109/CVPR.2019.00613Google ScholarCross Ref
- Jiawei Zhang, Jinshan Pan, Jimmy Ren, Yibing Song, Linchao Bao, Rynson WH Lau, and Ming-Hsuan Yang. 2018. Dynamic scene deblurring using spatially variant recurrent neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2521–2529.Google ScholarCross Ref
- Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Bjorn Stenger, Wei Liu, and Hongdong Li. 2020. Deblurring by realistic blurring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2737–2746. https://doi.org/10.48550/arXiv.2004.01860Google ScholarCross Ref
Index Terms
- A feature catcher with excellent deblurring effects
Recommendations
Deep non-blind deblurring network for saturated blurry images
AbstractNon-blind image deblurring has attracted a lot of attention in the field of low-level vision. However, the existing non-blind deblurring methods cannot effectively deal with a saturated blurry image. The key point is that the degradation model of ...
Spatially variant defocus blur map estimation and deblurring from a single image
A blur map estimation method using edge information is proposed.The blur map is segmented into multiple superpixels according to the image contours.Ringing artifacts and noise are detected and removed after deconvolution. In this paper, we propose a ...
CDMC-Net: Context-Aware Image Deblurring Using a Multi-scale Cascaded Network
AbstractImage deblurring is a widely researched topic in low-level vision. Over the last few years, many researchers try to deblur by stacking multi-scale pyramid structures, which inevitably increases the computational complexity. In addition, most of ...
Comments