ABSTRACT
Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of information. Besides, existing methods always use a multi-supervised method to aggregate different feature maps, which can not effectively aggregate hierarchical feature information. To address these issues, we propose an attention cube network (A-CubeNet) for image restoration for more powerful feature expression and feature correlation learning. Specifically, we design a novel attention mechanism from three dimensions, namely spatial dimension, channel-wise dimension and hierarchical dimension. The adaptive spatial attention branch (ASAB) and the adaptive channel attention branch (ACAB) constitute the adaptive dual attention module (ADAM), which can capture the long-range spatial and channel-wise contextual information to expand the receptive field and distinguish different types of information for more effective feature representations. Furthermore, the adaptive hierarchical attention module (AHAM) can capture the long-range hierarchical contextual information to flexibly aggregate different feature maps by weights depending on the global context. The ADAM and AHAM cooperate to form an 'attention in attention' structure, which means AHAM's inputs are enhanced by ASAB and ACAB. Experiments demonstrate the superiority of our method over state-of-the-art image restoration methods in both quantitative comparison and visual analysis.
Supplemental Material
- Eirikur Agustsson and Radu Timofte. 2017. Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 126--135.Google ScholarCross Ref
- Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn. 2018. Fast, accurate, and lightweight super-resolution with cascading residual network. In Proceedings of the European Conference on Computer Vision (ECCV). 252--268.Google ScholarDigital Library
- Marco Bevilacqua, Aline Roumy, Christine Guillemot, and Marie line Alberi Morel. 2012. Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding. In Proceedings of the British Machine Vision Conference (BMVC). 135.1--135.10.Google ScholarCross Ref
- Yunjin Chen and Thomas Pock. 2016. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 6 (2016), 1256--1272.Google ScholarDigital Library
- Jae-Seok Choi and Munchurl Kim. 2017. A deep convolutional neural network with selection units for super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 154--160.Google ScholarCross Ref
- Xiangxiang Chu, Bo Zhang, Hailong Ma, Ruijun Xu, Jixiang Li, and Qingyuan Li. 2019. Fast, accurate and lightweight super-resolution with neural architecture search. arXiv preprint arXiv:1901.07261 (2019).Google Scholar
- Xiangxiang Chu, Bo Zhang, Ruijun Xu, and Hailong Ma. 2019. Multi-objective reinforced evolution in mobile neural architecture search. arXiv preprint arXiv:1901.01074 (2019).Google Scholar
- Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, and Karen Egiazarian. 2007. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing 16, 8 (2007), 2080--2095.Google ScholarCross Ref
- Tao Dai, Jianrui Cai, Yongbing Zhang, Shu-Tao Xia, and Lei Zhang. 2019. Secondorder attention network for single image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11065--11074.Google Scholar
- Chao Dong, Yubin Deng, Chen Change Loy, and Xiaoou Tang. 2015. Compression artifacts reduction by a deep convolutional network. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 576--584.Google ScholarDigital Library
- Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2014. Learning a deep convolutional network for image super-resolution. In Proceedings of the European Conference on Computer Vision (ECCV). 184--199.Google ScholarCross Ref
- Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2015. Image superresolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 2 (2015), 295--307.Google ScholarDigital Library
- Chao Dong, Chen Change Loy, and Xiaoou Tang. 2016. Accelerating the superresolution convolutional neural network. In Proceedings of the European Conference on Computer Vision (ECCV). 391--407.Google Scholar
- A. Foi, V. Katkovnik, and K. Egiazarian. 2007. Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images. IEEE Transactions on Image Processing 16, 5 (2007), 1395--1411.Google ScholarDigital Library
- Shi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, and Lei Zhang. 2019. Toward convolutional blind denoising of real photographs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1712--1722.Google ScholarCross Ref
- Muhammad Haris, Gregory Shakhnarovich, and Norimichi Ukita. 2018. Deep back-projection networks for super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1664--1673.Google ScholarCross Ref
- Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7132--7141.Google ScholarCross Ref
- Yanting Hu, Jie Li, Yuanfei Huang, and Xinbo Gao. 2019. Channel-wise and spatial feature modulation network for single image super-resolution. IEEE Transactions on Circuits and Systems for Video Technology (2019).Google Scholar
- Jia Bin Huang, Abhishek Singh, and Narendra Ahuja. 2015. Single Image Super resolution from Transformed Self-Exemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5197--5206.Google ScholarCross Ref
- Zheng Hui, Xinbo Gao, Yunchu Yang, and Xiumei Wang. 2019. Lightweight image super-resolution with information multi-distillation network. In Proceedings of the 27th ACM International Conference on Multimedia (ACM MM). 2024--2032.Google ScholarDigital Library
- Zheng Hui, Xiumei Wang, and Xinbo Gao. 2018. Fast and accurate single image super-resolution via information distillation network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 723--731.Google ScholarCross Ref
- Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Accurate image superresolution using very deep convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1646--1654.Google ScholarCross Ref
- Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Deeply-recursive convolutional network for image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1637--1645.Google ScholarCross Ref
- Jun-Hyuk Kim, Jun-Ho Choi, Manri Cheon, and Jong-Seok Lee. 2018. Ram: Residual attention module for single image super-resolution. arXiv preprint arXiv:1811.12043 (2018).Google Scholar
- Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang. 2017. Deep laplacian pyramid networks for fast and accurate super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 624--632.Google ScholarCross Ref
- Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. 2017. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4681--4690.Google ScholarCross Ref
- Juncheng Li, Faming Fang, Kangfu Mei, and Guixu Zhang. 2018. Multi-scale residual network for image super-resolution. In Proceedings of the European Conference on Computer Vision (ECCV). 517--532.Google ScholarCross Ref
- Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. 2017. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 136--144.Google ScholarCross Ref
- Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, and Thomas S Huang. 2018. Non-local recurrent network for image restoration. In Advances in Neural Information Processing Systems (NeurIPS). 1673--1682.Google Scholar
- Pengju Liu, Hongzhi Zhang, Kai Zhang, Liang Lin, and Wangmeng Zuo. 2018. Multi-level wavelet-CNN for image restoration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 773--782.Google ScholarCross Ref
- D. Martin, C. Fowlkes, D. Tal, and J. Malik. 2002. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 416--423.Google Scholar
- Yusuke Matsui, Kota Ito, Yuji Aramaki, Azuma Fujimoto, Toru Ogawa, Toshihiko Yamasaki, and Kiyoharu Aizawa. 2017. Sketch-based manga retrieval using manga109 dataset. Multimedia Tools and Applications (2017).Google Scholar
- Volodymyr Mnih, Nicolas Heess, Alex Graves, et al. 2014. Recurrent models of visual attention. In Advances in Neural Information Processing Systems (NeurIPS). 2204--2212.Google Scholar
- A. K. Moorthy and A. C. Bovik. 2009. Visual Importance Pooling for Image Quality Assessment. IEEE Journal of Selected Topics in Signal Processing 3, 2 (2009), 193--201.Google ScholarCross Ref
- Wenzhe Shi, Jose Caballero, Ferenc Huszár, Johannes Totz, Andrew P Aitken, Rob Bishop, Daniel Rueckert, and Zehan Wang. 2016. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1874--1883.Google ScholarCross Ref
- Ying Tai, Jian Yang, and Xiaoming Liu. 2017. Image super-resolution via deep recursive residual network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3147--3155.Google ScholarCross Ref
- Ying Tai, Jian Yang, Xiaoming Liu, and Chunyan Xu. 2017. Memnet: A persistent memory network for image restoration. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 4539--4547.Google ScholarCross Ref
- Tong Tong, Gen Li, Xiejie Liu, and Qinquan Gao. 2017. Image super-resolution using dense skip connections. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 4799--4807.Google ScholarCross Ref
- Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He. 2018. Non-local neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7794--7803.Google ScholarCross Ref
- Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV). 3--19.Google ScholarDigital Library
- Roman Zeyde, Michael Elad, and Matan Protter. 2010. On Single Image Scale-Up Using Sparse-Representations. In International Conference on Curves and Surfaces (ICCS). 711--730.Google Scholar
- Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing 26, 7 (2017), 3142--3155.Google ScholarDigital Library
- Kai Zhang, Wangmeng Zuo, Shuhang Gu, and Lei Zhang. 2017. Learning deep CNN denoiser prior for image restoration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3929--3938.Google ScholarCross Ref
- Kai Zhang, Wangmeng Zuo, and Lei Zhang. 2018. FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing 27, 9 (2018), 4608--4622.Google ScholarCross Ref
- Kai Zhang, Wangmeng Zuo, and Lei Zhang. 2018. Learning a single convolutional super-resolution network for multiple degradations. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3262--3271.Google ScholarCross Ref
- Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. 2018. Image super-resolution using very deep residual channel attention networks. In Proceedings of the European Conference on Computer Vision (ECCV). 286--301.Google ScholarDigital Library
- Yulun Zhang, Kunpeng Li, Kai Li, Bineng Zhong, and Yun Fu. 2019. Residual non-local attention networks for image restoration. In International Conference on Learning Representations (ICLR).Google Scholar
- Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. 2018. Residual dense network for image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2472--2481.Google ScholarCross Ref
Index Terms
- Attention Cube Network for Image Restoration
Recommendations
Mix-order Attention Networks for Image Restoration
MM '21: Proceedings of the 29th ACM International Conference on MultimediaConvolutional neural networks (CNNs) have obtained great success in image restoration tasks, like single image denoising, demosaicing, and super-resolution. However, most existing CNN-based methods neglect the diversity of image contents and ...
Image Restoration Using Gaussian Scale Mixtures in Complex Curvelet Transform Domain
ICMTMA '10: Proceedings of the 2010 International Conference on Measuring Technology and Mechatronics Automation - Volume 02In this paper, a complex Curvelet transform is presented at first. The key innovation can be generalized as follows:2D and 1D complex wavelet transform instead à trous algorithm sub-band decomposition and ID wavelet transform respectively, and increase ...
Dual-domain strip attention for image restoration
AbstractImage restoration aims to reconstruct a latent high-quality image from a degraded observation. Recently, the usage of Transformer has significantly advanced the state-of-the-art performance of various image restoration tasks due to its powerful ...
Comments