Abstract
Depth image denoising is increasingly becoming the hot research topic nowadays, because it reflects the three-dimensional scene and can be applied in various fields of computer vision. But the depth images obtained from depth camera usually contain stains such as noise, which greatly impairs the performance of depth-related applications. In this article, considering that group-based image restoration methods are more effective in gathering the similarity among patches, a group-based nuclear norm and learning graph (GNNLG) model was proposed. For each patch, we find and group the most similar patches within a searching window. The intrinsic low-rank property of the grouped patches is exploited in our model. In addition, we studied the manifold learning method and devised an effective optimized learning strategy to obtain the graph Laplacian matrix, which reflects the topological structure of image, to further impose the smoothing priors to the denoised depth image. To achieve fast speed and high convergence, the alternating direction method of multipliers is proposed to solve our GNNLG. The experimental results show that the proposed method is superior to other current state-of-the-art denoising methods in both subjective and objective criterion.
- Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3, 1 (2011), 1--122.Google ScholarDigital Library
- Antoni Buades, Bartomeu Coll, and Jean Michel Morel. 2005. A non-local algorithm for image denoising. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2005 (CVPR’05), Vol. 2. 60--65.Google ScholarDigital Library
- Antoni Buades, Bartomeu Coll, and Jean-Michel Morel. 2005. A review of image denoising algorithms, with a new one. Multiscale Model. Simul. 4, 2 (2005), 490--530.Google ScholarCross Ref
- Emmanuel J. Candes and Yaniv Plan. 2010. Matrix completion with noise. Proc. IEEE 98, 6 (2010), 925--936.Google ScholarCross Ref
- Bindita Chaudhuri, Begüm Demir, Lorenzo Bruzzone, and Subhasis Chaudhuri. 2016. Region-based retrieval of remote sensing images using an unsupervised graph-theoretic approach. IEEE Geosci. Remote Sens. Lett. 13, 7 (2016), 987--991.Google ScholarCross Ref
- Rong Chen, Xianming Liu, Deming Zhai, and Debin Zhao. 2017. Depth image denoising via collaborative graph fourier transform. In International Forum on Digital TV and Wireless Multimedia Communications. Springer, 128--137.Google Scholar
- Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, and Karen Egiazarian. 2007. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16, 8 (2007), 2080--2095.Google ScholarCross Ref
- Cheng Deng, Rongrong Ji, Dacheng Tao, Xinbo Gao, and Xuelong Li. 2014. Weakly supervised multi-graph learning for robust image reranking. IEEE Trans. Multimedia 16, 3 (2014), 785--795.Google ScholarDigital Library
- Weisheng Dong, Xin Li, Lei Zhang, and Guangming Shi. 2011. Sparsity-based image denoising via dictionary learning and structural clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 457--464.Google ScholarDigital Library
- Weisheng Dong, Guangming Shi, Xin Li, Kefan Peng, Jinjian Wu, and Zhenhua Guo. 2016. Color-guided depth recovery via joint local structural and nonlocal low-rank regularization. IEEE Trans. Multimedia 19, 2 (2016), 293–301.Google ScholarDigital Library
- M. Elad and M. Aharon. 2006. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process. 15, 12 (2006), 3736--3745.Google ScholarDigital Library
- Anupriya Gogna, Ankita Shukla, H. K. Agarwal, and Angshul Majumdar. 2014. Split Bregman algorithms for sparse/joint-sparse and low-rank signal recovery: Application in compressive hyperspectral imaging. In Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP’14). IEEE, 1302--1306.Google ScholarCross Ref
- Ke Gu, Guangtao Zhai, Xiaokang Yang, and Wenjun Zhang. 2015. Using free energy principle for blind image quality assessment. IEEE Trans. Multimedia 17, 1 (2015), 50--63.Google ScholarCross Ref
- Shuhang Gu, Lei Zhang, Wangmeng Zuo, and Xiangchu Feng. 2014. Weighted nuclear norm minimization with application to image denoising. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2862--2869.Google ScholarDigital Library
- Binbin Hao, Jianguang Zhu, and Yan Hao. 2014. Iterative total variation image deblurring with varying regularized parameter. In Proceedings of the 2014 Sixth International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC’14), Vol. 1. IEEE, 249--252.Google ScholarDigital Library
- Wei Hu, Xin Li, Gene Cheung, and Oscar Au. 2013. Depth map denoising using graph-based transform and group sparsity. In Proceedings of the 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP’13). IEEE, 001--006.Google ScholarCross Ref
- De An Huang, Li Wei Kang, Yu Chiang Frank Wang, and Chia Wen Lin. 2013. Self-learning based image decomposition with applications to single image denoising. IEEE Trans. Multimedia 16, 1 (2013), 83--93.Google ScholarCross Ref
- Hui Ji, Chaoqiang Liu, Zuowei Shen, and Yuhong Xu. 2010. Robust video denoising using low rank matrix completion. In Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’10). IEEE, 1791--1798.Google ScholarCross Ref
- Vassilis Kalofolias, Xavier Bresson, Michael Bronstein, and Pierre Vandergheynst. 2014. Matrix completion on graphs. arXiv:1408.1717 Retrieved from http://arxiv.org/abs/1408.1717.Google Scholar
- Ulugbek S. Kamilov. 2017. A parallel proximal algorithm for anisotropic total variation minimization. IEEE Transac. Image Process. 26, 2 (2017), 539--548.Google ScholarDigital Library
- Charles Kervrann and Jérôme Boulanger. 2006. Optimal spatial adaptation for patch-based image denoising. IEEE Trans. Image Process. 15, 10 (2006), 2866--2878.Google ScholarDigital Library
- ZhiSheng Li, Bingtao Liu, and Chenggang Yan. 2019. CFMDA: Collaborative filtering-based MiRNA-disease association prediction. Multimedia Tools Appl. 78, 1 (2019), 605–618.Google ScholarDigital Library
- Jun Liu, Xue-Cheng Tai, Haiyang Huang, and Zhongdan Huan. 2013. A weighted dictionary learning model for denoising images corrupted by mixed noise. IEEE Trans. Image Process. 22, 3 (2013), 1108--1120.Google ScholarDigital Library
- Xianming Liu, Gene Cheung, Xiaolin Wu, and Debin Zhao. 2017. Random walk graph Laplacian-based smoothness prior for soft decoding of JPEG images. IEEE Trans. Image Process. 26, 2 (2017), 509--524.Google ScholarDigital Library
- Yipeng Liu, Zhen Long, and Ce Zhu. 2018. Image completion using low tensor tree rank and total variation minimization. IEEE Trans. Multimedia 21, 2 (2018), 338–350.Google ScholarDigital Library
- Si Lu, Xiaofeng Ren, and Feng Liu. 2014. Depth enhancement via low-rank matrix completion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3390--3397.Google ScholarDigital Library
- Julien Mairal, Michael Elad, and Guillermo Sapiro. 2007. Sparse representation for color image restoration. IEEE Trans. Image Process. 17, 1 (2007), 53--69.Google ScholarDigital Library
- Stéphane G. Mallat and Zhifeng Zhang. 1993. Matching pursuits with time-frequency dictionaries. IEEE Trans. Sign. Process. 41, 12 (1993), 3397--3415.Google ScholarDigital Library
- Françcois Rousseau, Piotr A. Habas, and Colin Studholme. 2011. A supervised patch-based approach for human brain labeling. IEEE Trans. Med. Imag. 30, 10 (2011), 1852--1862.Google ScholarCross Ref
- Ivan Selesnick. 2017. Total variation denoising via the Moreau envelope. IEEE Sign. Process. Lett. 24, 2 (2017), 216--220.Google ScholarCross Ref
- Mark J. Shensa. 1992. The discrete wavelet transform: Wedding the a trous and Mallat algorithms. IEEE Trans. Sign. Process. 40, 10 (1992), 2464--2482.Google ScholarDigital Library
- Jean-Luc Starck, D. L. Donoho, and Michael Elad. 2004. Redundant Multiscale Transforms and Their Application for morphological Component Separation. Technical Report. CM-P00052061.Google Scholar
- Dong Tian, Po-Lin Lai, Patrick Lopez, and Cristina Gomila. 2009. View synthesis techniques for 3D video. In Applications of Digital Image Processing XXXII, Vol. 7443. International Society for Optics and Photonics, 74430T.Google ScholarCross Ref
- Diego Tomassi, Diego Milone, and James D. B. Nelson. 2015. Wavelet shrinkage using adaptive structured sparsity constraints. Sign. Process. 106 (2015), 73--87.Google ScholarDigital Library
- Qiong Wang, Xinggan Zhang, Yu Wu, Lan Tang, and Zhiyuan Zha. 2017. Nonconvex weighted ℓp minimization based group sparse representation framework for image denoising. IEEE Signal Processing Letters 24, 11 (2017), 1686–1690.Google ScholarCross Ref
- Shuyang Wang, Zhengming Ding, and Yun Fu. 2017. Marginalized denoising dictionary learning with locality constraint. IEEE Transactions on Image Processing 27, 1 (2017), 500–510.Google ScholarCross Ref
- Shiping Wang and Wenzhong Guo. 2017. Sparse multigraph embedding for multimodal feature representation. IEEE Transactions on Multimedia 19, 7 (2017), 1454–1466.Google ScholarDigital Library
- Jun Xie, Rogerio Schmidt Feris, Shiaw Shian Yu, and Ming Ting Sun. 2015. Joint super resolution and denoising from a single depth image. IEEE Trans. Multimedia 17, 9 (2015), 1525--1537.Google ScholarDigital Library
- Hongyang Xue, Shengming Zhang, and Deng Cai. 2017. Depth image inpainting: Improving low rank matrix completion with low gradient regularization. IEEE Trans. Image Process. 26, 9 (2017), 4311--4320.Google ScholarDigital Library
- Chenggang Yan, Biao Gong, Yuxuan Wei, and Yue Gao. 2020. Deep multi-view enhancement hashing for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020).Google ScholarCross Ref
- C. Yan, L. Li, C. Zhang, B. Liu, Y. Zhang, and Q. Dai. 2019. Cross-modality bridging and knowledge transferring for image understanding. IEEE Trans. Multimedia 21, 10 (2019), 2675--2685.Google ScholarDigital Library
- C. Yan, B. Shao, H. Zhao, R. Ning, Y. Zhang, and F. Xu. 2020. 3D room layout estimation from a single RGB image. (unpublished).Google Scholar
- C. Yan, Y. Tu, X. Wang, Y. Zhang, X. Hao, Y. Zhang, and Q. Dai. 2020. STAT: Spatial-temporal attention mechanism for video captioning. IEEE Trans. Multimedia 22, 1 (2020), 229--241.Google ScholarDigital Library
- C. Yan, H. Xie, J. Chen, Z. Zha, X. Hao, Y. Zhang, and Q. Dai. 2018. A fast uyghur text detector for complex background images. IEEE Trans. Multimedia 20, 12 (2018), 3389--3398.Google ScholarDigital Library
- Yael Yankelevsky and Michael Elad. 2017. Dual graph regularized dictionary learning. IEEE Trans. Sign. Inf. Process. Netw. 2, 4 (2017), 611--624.Google Scholar
- Jian Zhang, Debin Zhao, and Wen Gao. 2014. Group-based sparse representation for image restoration. IEEE Trans. Image Process. 23, 8 (2014), 3336--3351.Google ScholarCross Ref
- 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 Trans. Image Process. 26, 7 (2017), 3142--3155.Google ScholarDigital Library
- Xuande Zhang, Xiangchu Feng, and Weiwei Wang. 2013. Two-direction nonlocal model for image denoising. IEEE Trans. Image Process. 22, 1 (2013), 408--412.Google ScholarDigital Library
- Zhiliang Zhu, Fangda Guo, Hai Yu, and Chen Chen. 2014. Fast single image super-resolution via self-example learning and sparse representation. IEEE Trans. Multimedia 16, 8 (2014), 2178--2190.Google ScholarCross Ref
Index Terms
- Depth Image Denoising Using Nuclear Norm and Learning Graph Model
Recommendations
Nonlocal image denoising via adaptive tensor nuclear norm minimization
Nonlocal self-similarity shows great potential in image denoising. Therefore, the denoising performance can be attained by accurately exploiting the nonlocal prior. In this paper, we model nonlocal similar patches through the multi-linear approach and ...
Non-convex weighted ℓ p nuclear norm based ADMM framework for image restoration
AbstractInspired by the fact that the matrix formed by nonlocal similar patches in a natural image is of low rank, the nuclear norm minimization (NNM) has been widely used in various image processing studies. Nonetheless, nuclear norm based ...
Denoising by low-rank and sparse representations
A nonlocal image denoising approach using sparsity and low-rank priors is proposed.A parameter-free optimal singular value shrinker is introduced for low-rank modeling.An iterative patch-based low-rank regularized collaborative filtering is developed.A ...
Comments