Li, J. and Zhang, J. and Maybank, Stephen (2022) Bridging composite and real: towards end-to-end deep image matting. International Journal of Computer Vision 130 , pp. 246-266. ISSN 0920-5691.
|
Text
BridgingCompositeAndReal.pdf - Author's Accepted Manuscript Download (8MB) | Preview |
Abstract
Extracting accurate foregrounds from natural images benefits many downstream applications such as film production and augmented reality. However, the furry characteristics and various appearance of the foregrounds, e.g., animal and portrait, challenge existing matting methods, which usually require extra user inputs such as trimap or scribbles. To resolve these problems, we study the distinct roles of semantics and details for image matting and decompose the task into two parallel sub-tasks: high-level semantic segmentation and low-level details matting. Specifically, we propose a novel glance and Focus Matting network (GFM), which employs a shared encoder and two separate decoders to learn both tasks in a collaborative manner for end-to-end natural image matting. Besides, due to the limitation of available natural images in the matting task, previous methods typically adopt composite images for training and evaluation, which result in limited generalization ability on real-world images. In this paper, we investigate the domain gap issue between composite images and real-world images systematically by conducting comprehensive analyses of various discrepancies between the foreground and background images. We find that a carefully desinged composition route RSSN that aims to reduce the discepancies can lead to a better model with remarkable generalization ability . Furthermore, we provide a bench mark containing 2,000 high-resolution real-world animal images and 10,000 portrait images along with their manually labelled alpha mattes to serve as a test bed for evaluating matting model's generalization ability on real-world images. Comprehensive empirical studies have demonstrated that GFM outperforms state-of-the-art methods and effectively reduces the generalization error. The code and the datasets will be released at https://github.com/JizhiziLi/GFM.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | Image Matting, Deep Learning, Alpha matte, Image Composition, Domain Gap |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
| Depositing User: | Steve Maybank |
| Date Deposited: | 15 Nov 2021 12:01 |
| Last Modified: | 09 Aug 2023 12:52 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/46501 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
