File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Learning Transparent Object Matting

TitleLearning Transparent Object Matting
Authors
KeywordsConvolutional neural network
Image matting
Transparent object
Issue Date2019
PublisherSpringer New York LLC. The Journal's web site is located at http://springerlink.metapress.com/openurl.asp?genre=journal&issn=0920-5691
Citation
International Journal of Computer Vision, 2019, v. 127 n. 10, p. 1527-1544 How to Cite?
AbstractThis paper addresses the problem of image matting for transparent objects. Existing approaches often require tedious capturing procedures and long processing time, which limit their practical use. In this paper, we formulate transparent object matting as a refractive flow estimation problem, and propose a deep learning framework, called TOM-Net, for learning the refractive flow. Our framework comprises two parts, namely a multi-scale encoder-decoder network for producing a coarse prediction, and a residual network for refinement. At test time, TOM-Net takes a single image as input, and outputs a matte (consisting of an object mask, an attenuation mask and a refractive flow field) in a fast feed-forward pass. As no off-the-shelf dataset is available for transparent object matting, we create a large-scale synthetic dataset consisting of 178 K images of transparent objects rendered in front of images sampled from the Microsoft COCO dataset. We also capture a real dataset consisting of 876 samples using 14 transparent objects and 60 background images. Besides, we show that our method can be easily extended to handle the cases where a trimap or a background image is available. Promising experimental results have been achieved on both synthetic and real data, which clearly demonstrate the effectiveness of our approach. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.
Persistent Identifierhttp://hdl.handle.net/10722/274271
ISSN
2017 Impact Factor: 11.541
2015 SCImago Journal Rankings: 5.633

 

DC FieldValueLanguage
dc.contributor.authorChen, G-
dc.contributor.authorHan, K-
dc.contributor.authorWong, KKY-
dc.date.accessioned2019-08-18T14:58:28Z-
dc.date.available2019-08-18T14:58:28Z-
dc.date.issued2019-
dc.identifier.citationInternational Journal of Computer Vision, 2019, v. 127 n. 10, p. 1527-1544-
dc.identifier.issn0920-5691-
dc.identifier.urihttp://hdl.handle.net/10722/274271-
dc.description.abstractThis paper addresses the problem of image matting for transparent objects. Existing approaches often require tedious capturing procedures and long processing time, which limit their practical use. In this paper, we formulate transparent object matting as a refractive flow estimation problem, and propose a deep learning framework, called TOM-Net, for learning the refractive flow. Our framework comprises two parts, namely a multi-scale encoder-decoder network for producing a coarse prediction, and a residual network for refinement. At test time, TOM-Net takes a single image as input, and outputs a matte (consisting of an object mask, an attenuation mask and a refractive flow field) in a fast feed-forward pass. As no off-the-shelf dataset is available for transparent object matting, we create a large-scale synthetic dataset consisting of 178 K images of transparent objects rendered in front of images sampled from the Microsoft COCO dataset. We also capture a real dataset consisting of 876 samples using 14 transparent objects and 60 background images. Besides, we show that our method can be easily extended to handle the cases where a trimap or a background image is available. Promising experimental results have been achieved on both synthetic and real data, which clearly demonstrate the effectiveness of our approach. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.-
dc.languageeng-
dc.publisherSpringer New York LLC. The Journal's web site is located at http://springerlink.metapress.com/openurl.asp?genre=journal&issn=0920-5691-
dc.relation.ispartofInternational Journal of Computer Vision-
dc.subjectConvolutional neural network-
dc.subjectImage matting-
dc.subjectTransparent object-
dc.titleLearning Transparent Object Matting-
dc.typeArticle-
dc.identifier.emailWong, KKY: kykwong@cs.hku.hk-
dc.identifier.authorityWong, KKY=rp01393-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/s11263-019-01202-3-
dc.identifier.scopuseid_2-s2.0-85070207145-
dc.identifier.hkuros301496-
dc.identifier.volume127-
dc.identifier.issue10-
dc.identifier.spage1527-
dc.identifier.epage1544-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats