Abstract
This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Many approaches achieve alpha mattes with complex encoders to extract robust semantics, then resort to the U-net-like decoder to concatenate or fuse encoder features. However, image matting is essentially a pixel-wise regression, and the ideal situation is to perceive the maximum opacity correspondence from the input image. In this paper, we argue that the high-resolution feature representation, perception and communication are more crucial for matting accuracy. Therefore, we propose an Intensive Integration and Global Foreground Perception network (I2GFP) to integrate wider and higher feature streams. Wider means we combine intensive features in each decoder stage, while higher suggests we retain high-resolution intermediate features and perceive large-scale foreground appearance. Our motivation sacrifices model depth for a significant performance promotion. We perform extensive experiments to prove the proposed I2GFP model, and state-of-the-art results can be achieved on different public datasets.
Y. Qiao and Z. Wei—contribute equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cai, S., et al.: Disentangled image matting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8819–8828 (2019)
Cho, D., Tai, Y.-W., Kweon, I.: Natural image matting using deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 626–643. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_39
Dai, Y., Lu, H., Shen, C.: Learning affinity-aware upsampling for deep image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6841–6850 (2021)
Gastal, E.S.L., et al.: Shared sampling for real-time alpha matting. Comput. Graph. Forum 29, 575–584 (2010). https://doi.org/10.1111/j.1467-8659.2009.01627.x
Hou, Q., Liu, F.: Context-aware image matting for simultaneous foreground and alpha estimation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4130–4139 (2019)
Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 228–242 (2008). https://doi.org/10.1109/TPAMI.2007.1177
Li, Y., Lu, H.: Natural image matting via guided contextual attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11450–11457 (2020)
Lin, S., Ryabtsev, A., Sengupta, S., Curless, B.L., et al.: Real-time high-resolution background matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8762–8771 (2021)
Lu, H., Dai, Y., Shen, C., Xu, S.: Indices matter: learning to index for deep image matting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3266–3275 (2019)
Peng, C., Zhang, X., Yu, G., et al.: Large kernel matters-improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4353–4361 (2017)
Qiao, Y., Liu, Y., Yang, X., Zhou, D., et al.: Attention-guided hierarchical structure aggregation for image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13676–13685 (2020)
Qiao, Y., et al.: Multi-scale information assembly for image matting. Comput. Graph. Forum 39, 565–574 (2020). https://doi.org/10.1111/cgf.14168
Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1826–1833 (2009)
Sun, Y., et al.: Semantic image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11120–11129 (2021)
Tang, J., Aksoy, Y., Oztireli, C., Gross, M., Aydin, T.O.: Learning-based sampling for natural image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3055–3063 (2019)
Wei, T., Chen, D., Zhou, W., et al.: Improved image matting via real-time user clicks and uncertainty estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15374–15383 (2021)
Xu, N., Price, B., et al.: Deep image matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2970–2979 (2017)
Yang, X., Xu, K., Chen, S., et al.: Active matting. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 4595–4605 (2018)
Yu, Q., Zhang, J., Zhang, H., et al.: Mask guided matting via progressive refinement network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1154–1163 (2021)
Yu, Z., Li, X., Huang, H., Zheng, W., Chen, L.: Cascade image matting with deformable graph refinement. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7167–7176 (2021)
Zhang, Q., Cong, R., Li, C., et al.: Dense attention fluid network for salient object detection in optical remote sensing images. IEEE Trans. Image Process. 30, 1305–1317 (2021). https://doi.org/10.1109/TIP.2020.3042084
Zhang, Y., et al.: A late fusion CNN for digital matting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7469–7478 (2019)
Zhang, Z., Ma, J., Xu, P., Wang, W.: Dense attention-guided network for boundary-aware salient object detection. In: Lokoč, J., et al. (eds.) MMM 2021. LNCS, vol. 12572, pp. 148–161. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67832-6_13
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Qiao, Y. et al. (2022). Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting. In: Magnenat-Thalmann, N., et al. Advances in Computer Graphics. CGI 2022. Lecture Notes in Computer Science, vol 13443. Springer, Cham. https://doi.org/10.1007/978-3-031-23473-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-23473-6_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23472-9
Online ISBN: 978-3-031-23473-6
eBook Packages: Computer ScienceComputer Science (R0)