Qiao, YuLiu, YuhaoZhu, QiangYang, XinWang, YuxinZhang, QiangWei, XiaopengEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lue2020-10-292020-10-2920201467-8659https://doi.org/10.1111/cgf.14168https://diglib.eg.org:443/handle/10.1111/cgf14168Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images.We argue that the foreground objects can be represented by different-level information, including the central bodies, large-grained boundaries, refined details, etc. Based on this observation, in this paper, we propose a multi-scale information assembly framework (MSIA-matte) to pull out high-quality alpha mattes from single RGB images. Technically speaking, given an input image, we extract advanced semantics as our subject content and retain initial CNN features to encode different-level foreground expression, then combine them by our well-designed information assembly strategy. Extensive experiments can prove the effectiveness of the proposed MSIA-matte, and we can achieve state-of-the-art performance compared to most existing matting networks.Computing methodologiesImage segmentationImage representations10.1111/cgf.14168565-574