Image Matting 抠图算法

1. Image Matting综述

• Image Matting传统方法和深度学习方法回顾

2. Image Matting经典算法

2017

• DIM：Deep Image Matting [1]

2018

• AlphaGAN [2]

2019

• SampleNet [3]
• Context-Aware [4]
• IndexNet [5]

2020

• HAttMatting [6]
  参考博客：CVPR2020 | HAttMatting，让抠图变得如此简单！
• background matting [7]
  创新点：以去除前景的背景图片代替trimap
  参考博客： 2020 CVPR之image matting：Background Matting：The World is Your Green Screen
• MODNet [8]
  创新点：无需trimap
  参考博客：MODNet

【参考文献】：

[1] Ning Xu, Brian Price, Scott Cohen and Thomas Huang. “Deep Image Matting.” The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[2] S. Lutz, K. Amplianitis, and A. Smolic. “AlphaGAN: Generative Adversarial Networks for Natural Image Matting.” The British Machine Vision Conference (BMVC), 2018.
[3] Jingwei Tang, Yagiz Aksoy, Cengiz Oztireli, Markus Gross, and Tunc Ozan Aydin. Learning-based sampling for natural image matting. In CVPR, 2019.
[4] Qiqi Hou and Feng Liu. Context-aware image matting for simultaneous foreground and alpha estimation. In ICCV, 2019.
[5] Hao Lu, Yutong Dai, Chunhua Shen, and Songcen Xu. Indices matter: Learning to index for deep image matting. In ICCV, 2019.
[6] Yu Qiao, Yuhao Liu, Xin Yang, Dongsheng Zhou, Mingliang Xu, Qiang Zhang, and Xiaopeng Wei1. Attention-guided hierarchical structure aggregation for image matting. In CVPR, 2020.
[7] Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steve Seitz, and Ira Kemelmacher-Shlizerman. Background matting: The world is your green screen. In CVPR, 2020.
[8] Ke Z , Li K , Zhou Y , et al. Is a Green Screen Really Necessary for Real-Time Portrait Matting?[J]. 2020.

3. Image Matting工程实现

• 人像抠图：算法概述及工程实现（一）
• 人像抠图：算法概述及工程实现（二）