|Xin Yang||Dalian University of Technology|
|Ke Xu||Dalian University of Technology;City University of Hong Kong|
|Shaozhe Chen||Dalian University of Technology|
|Shengfeng He||South China University of Technology|
|Baocai Yin Yin||Dalian University of Technology|
|Rynson Lau||City University of Hong Kong|
Image matting is an ill-posed problem.To this end, the authors propose an active matting method with recurrent reinforcement learning.
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.