Abstract
Image matting is an essential image processing technology in computer vision with significant diverse practical applications, including image synthesis, webcasting, and movie production. Although some methods have been proposed to extract the alpha mattes, these methods are not sensitive enough to local complex regions with large differences between the input image and the ground-truth alpha matte. In this paper, we design a weight map generation algorithm, which extracts the local complex region of each image by measuring the local complex differences between the input image and the ground-truth alpha matte. For the weight consistency problem of the pixel-level loss function, we propose a loss function based on local complexity differences, which can strengthen the training on local regions of large complexity differences. Moreover, we design a local complexity difference matting approach on the basis of the presented loss function and weight map generation algorithm to improve the matting accuracy of local complexity difference images. To verify the validity of the proposed matting method, experiments were conducted on the composition-1 k matting evaluation data set produced by Adobe. Experimental results show that the proposed weight map generation algorithm can effectively extract the local complex regions. Our proposed matting method outperforms state-of-the-art matting methods in the cases of locally complexity difference images.
Similar content being viewed by others
References
Aksoy Y, Aydin TO, Pollefeys M, Zürich E, Zürich DR (2017) Designing effective inter-pixel information flow for natural image matting. In: IEEE conference on computer vision and pattern recognition (CVPR), 2017, IEEE, pp 228—236
Barron JT (2019) A general and adaptive robust loss function. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2019, IEEE, pp 4326–4334
Cai S, Zhang X, Fan H, Huang H, Liu J, Liu J, Liu J, Wang J, Sun J (2019) Disentangled image matting. In: IEEE international conference on computer vision (CV), 2019, IEEE, pp 8819–8828
Chen Q, Li D, Tang C (2013) KNN matting. IEEE Trans Pattern Anal Mach Intell 35(9):2175–2188
Cho D, Kim S, Tai YW, Kweon IS (2016) Automatic trimap generation and consistent matting for light-field images. IEEE Trans Pattern Anal Mach Intell 39(8):1504–1517
Cho D, Tai Y, Kweon IS, Daejeon K, Korea S (2016) Natural image matting using deep convolutional neural networks. Proceedings of European Conference on Computer Vision (ECCV) 2016:626–643
Cho D, Tai Y, Kweon IS (2019) Deep convolutional neural network for natural image matting using initial alpha mattes. IEEE Trans Image Process 28(3):1054–1067
Feng X, Liang X, Zhang Z (2016) A cluster sampling method for image matting via sparse coding. In: Proceedings of european conference on computer vision (ECCV), 2016, pp. 204–219
Feng F, Huang H, Wu Q, Ling X, Liang Y, Chai Z (2020) An alpha matting algorithm based on collaborative swarm optimization for high-resolution images. Sci Sin Inform 50(3):424–437
Gong M, Qian Y, Cheng L (2015) Integrated foreground segmentation and boundary matting for live videos. IEEE Trans Image Process 24(4):1356–1370
He K, Rhemann C, Rother C, Tang X, Sun J (2011) A global sampling method for alpha matting. In: IEEE conference on computer vision and pattern recognition (CVPR), 2011, IEEE, pp 2049–2056
Huang H, Liang Y, Yang X, Hao Z (2019) Pixel-level discrete multiobjective sampling for image matting. IEEE Trans Image Process 28(8):3739–3751
Karacan L, Erdem A, Erdem E (2017) Alpha matting with KL-divergence-based sparse sampling. IEEE Trans Image Process 26(9):4523–4536
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (LR), 2015, pp 1–15
Lee Y, Yang S (2018) Parallel block sequential closed-form matting with fan-shaped partitions. IEEE Trans Image Process 27(2):594–605
Levin A, Lischinski D, Weiss Y (2008) A closed-form solution to natural image matting. IEEE Trans Pattern Anal Mach Intell 30(2):228–242
Li L, Cai H, Zhang Y, Lin W, Kot AC, Sun X (2016) Sparse representation-based image quality index with adaptive sub-dictionaries. IEEE Trans Image Process 25(8):3775–3786
Liang Y, Huang H, Cai Z, Hao Z (2019) Multiobjective evolutionary optimization based on fuzzy multicriteria evaluation and decomposition for image matting. IEEE Trans Fuzzy Syst 27(5):1100–1111
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), 2015, IEEE, pp 3431–3440
Lu H, Dai Y, Shen C, Xu S (2021) Index networks. IEEE Trans Pattern Anal Mach Intell 44(1):242–255
Lutz S, Amplianitis K, Smolić A (2018) AlphaGAN: generative adversarial networks for natural image matting. In: IEEE conference on computer vision and pattern recognition (CVPR), 2018, IEEE, pp 3050–3058
Porter T, Duff T (1984) Compositing digital images. In: Proceedings of computer graphics and interactive techniques (CGIT), 1984, pp 253–259
Tang J, Aksoy Y, Oztireli C, Gross M, Aydin TO (2019) Learning-based sampling for natural image matting. In: IEEE conference on computer vision and pattern recognition (CVPR), 2019, IEEE, pp 3050–3058
Wang Y, Niu Y, Duan P, Lin J, Zheng Y (2018) Deep propagation-based image matting. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), 2018, pp 999–1006
Xu N, Price B, Cohen S, Huang T (2017) Deep image matting. In: IEEE conference on computer vision and pattern recognition (CVPR), 2017, IEEE, pp 311–320
Yoon D, Park J, Cho D (2020) Lightweight deep CNN for natural image matting via similarity-preserving knowledge distillation. IEEE Signal Process Lett 27:2139–2143
Yu J, Lin Z, Yang J, Shen X, Huang TS (2019) Generative image inpainting with contextual attention. In: IEEE conference on computer vision and pattern recognition (CVPR), 2018, IEEE, pp 5505–5514
Zhang T, Liu X, Gong L, Wang S, Niu X, Shen L (2021) Late fusion multiple kernel clustering with local kernel alignment maximization. IEEE Trans Multimedia:1–15
Zhao M, Li D, Shi Z, Du S, Li P, Hu J (2019) Blur feature extraction plus automatic KNN matting: a novel two stage blur region detection method for local motion blurred images. IEEE Access 7:181142–181151
Zou D, Chen X, Cao G, Wang X (2020) Unsupervised video matting via sparse and low-rank representation. IEEE Trans Pattern Anal Mach Intell 42(6):1501–1514
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (no. 61876207, no. 62002053 and no. 62162012), the Natural Science Foundation of Guizhou Province (no. QKHJCZK2022YB195), the Natural Science Foundation of Guizhou Minzu University (no. GZMUZK[2021]YB24), the Natural Science Foundation of Guangdong Province (no. 2022A1515011491 and no. 2021A0101180005), the Fundamental Research Funds for the Central Universities (no. 2020ZYGXZR014), the Youth Science and Technology Talents Cultivating Object of Guizhou Province (no. QJHKY2021104), the Science and Technology Support Program of Guizhou (no. QKHZC2021YB531), the Guangdong Basic and Applied Basic Research Foundation (no. 2019A1515111082), the Zhongshan Science and Technology Research Project of Social welfare (no. 2019B2010), the University Young Innovative Talent Project of Guangdong Province (no. 2019KQNCX186), the Key Research and Development Program of Zhongshan (no. 2019A4018).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Feng, F., Huang, H., Liu, D. et al. Local complexity difference matting based on weight map and alpha mattes. Multimed Tools Appl 81, 43357–43372 (2022). https://doi.org/10.1007/s11042-022-13223-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13223-1