{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tom-net-learning-transparent-object-matting","title":"TOM-Net: Learning Transparent Object Matting from a Single Image","arxiv_id":"1803.04636","date":"2018-03-13","proceeding":"CVPR 2018 6","authors":["Guan-Ying Chen","Kai Han","Kwan-Yee K. Wong"],"abstract":"This paper addresses the problem of transparent object matting. Existing\nimage matting approaches for transparent objects often require tedious\ncapturing procedures and long processing time, which limit their practical use.\nIn this paper, we first formulate transparent object matting as a refractive\nflow estimation problem. We then propose a deep learning framework, called\nTOM-Net, for learning the refractive flow. Our framework comprises two parts,\nnamely a multi-scale encoder-decoder network for producing a coarse prediction,\nand a residual network for refinement. At test time, TOM-Net takes a single\nimage as input, and outputs a matte (consisting of an object mask, an\nattenuation mask and a refractive flow field) in a fast feed-forward pass. As\nno off-the-shelf dataset is available for transparent object matting, we create\na large-scale synthetic dataset consisting of 158K images of transparent\nobjects rendered in front of images sampled from the Microsoft COCO dataset. We\nalso collect a real dataset consisting of 876 samples using 14 transparent\nobjects and 60 background images. Promising experimental results have been\nachieved on both synthetic and real data, which clearly demonstrate the\neffectiveness of our approach.","url_abs":"http://arxiv.org/abs/1803.04636v3","url_pdf":"http://arxiv.org/pdf/1803.04636v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tom-net-learning-transparent-object-matting","repo_url":"https://github.com/guanyingc/TOM-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"tom-net-learning-transparent-object-matting","repo_url":"https://github.com/MindSpore-scientific-2/code-3/tree/main/Tom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"tom-net-learning-transparent-object-matting","repo_url":"https://github.com/MindSpore-scientific/code-14/tree/main/Tom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-matting","task_name":"Image Matting"},{"task_slug":"object","task_name":"Object"},{"task_slug":"transparent-objects","task_name":"Transparent objects"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.04636","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}