Table of LinksAbstract and 1. IntroductionRelated WorksMaGGIe3.1. Efficient Masked Guided Instance Matting3.2. Feature-Matte Temporal ConsistencyInstance Matting Datasets4.1. Image Instance Matting and 4.2. Video Instance MattingExperiments5.1. Pre-training on image data5.2. Training on video dataDiscussion and References\Supplementary MaterialArchitecture detailsImage matting8.1. Dataset generation and preparation8.2. Training details8.3. Quantitative details8.4. More qualitative results on natural imagesVideo matting9.1. Dataset generation9.2. Training details9.3. Quantitative details9.4. More qualitative results8.2. Training details\ \ \ \:::infoAuthors:(1) Chuong Huynh, University of Maryland, College Park (chuonghm@cs.umd.edu);(2) Seoung Wug Oh, Adobe Research (seoh,jolee@adobe.com);(3) Abhinav Shrivastava, University of Maryland, College Park (abhinav@cs.umd.edu);(4) Joon-Young Lee, Adobe Research (jolee@adobe.com).::::::infoThis paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license.:::\