English

Multi-scale Information Assembly for Image Matting

Computer Vision and Pattern Recognition 2021-03-04 v2

Abstract

Image 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.

Keywords

Cite

@article{arxiv.2101.02391,
  title  = {Multi-scale Information Assembly for Image Matting},
  author = {Yu Qiao and Yuhao Liu and Qiang Zhu and Xin Yang and Yuxin Wang and Qiang Zhang and Xiaopeng Wei},
  journal= {arXiv preprint arXiv:2101.02391},
  year   = {2021}
}

Comments

Pacific Graphics 2020

R2 v1 2026-06-23T21:52:05.568Z