Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
12-2018
Abstract
Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms.
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Information Systems and Management
Publication
Proceedings of the Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada, December 2-8
Volume
31
First Page
1
Last Page
11
City or Country
USA
Citation
YANG, Xin; XU, Ke; CHEN, Shaozhe; HE, Shengfeng; YIN, Baocai; and LAU, Rynson.
Active matting. (2018). Proceedings of the Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada, December 2-8. 31, 1-11.
Available at: https://ink.library.smu.edu.sg/sis_research/8537
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons