File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/s11263-019-01202-3
- Scopus: eid_2-s2.0-85070207145
- WOS: WOS:000485320300008
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Learning Transparent Object Matting
Title | Learning Transparent Object Matting |
---|---|
Authors | |
Keywords | Convolutional neural network Image matting Transparent object |
Issue Date | 2019 |
Publisher | Springer 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? |
Abstract | This 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 Identifier | http://hdl.handle.net/10722/274271 |
ISSN | 2023 Impact Factor: 11.6 2023 SCImago Journal Rankings: 6.668 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, G | - |
dc.contributor.author | Han, K | - |
dc.contributor.author | Wong, KYK | - |
dc.date.accessioned | 2019-08-18T14:58:28Z | - |
dc.date.available | 2019-08-18T14:58:28Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | International Journal of Computer Vision, 2019, v. 127 n. 10, p. 1527-1544 | - |
dc.identifier.issn | 0920-5691 | - |
dc.identifier.uri | http://hdl.handle.net/10722/274271 | - |
dc.description.abstract | This 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.language | eng | - |
dc.publisher | Springer New York LLC. The Journal's web site is located at http://springerlink.metapress.com/openurl.asp?genre=journal&issn=0920-5691 | - |
dc.relation.ispartof | International Journal of Computer Vision | - |
dc.rights | This is a post-peer-review, pre-copyedit version of an article published in International Journal of Computer Vision. The final authenticated version is available online at: http://dx.doi.org/10.1007/s11263-019-01202-3 | - |
dc.subject | Convolutional neural network | - |
dc.subject | Image matting | - |
dc.subject | Transparent object | - |
dc.title | Learning Transparent Object Matting | - |
dc.type | Article | - |
dc.identifier.email | Chen, G: gychen@cs.hku.hk | - |
dc.identifier.email | Wong, KYK: kykwong@cs.hku.hk | - |
dc.identifier.authority | Wong, KYK=rp01393 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1007/s11263-019-01202-3 | - |
dc.identifier.scopus | eid_2-s2.0-85070207145 | - |
dc.identifier.hkuros | 301496 | - |
dc.identifier.volume | 127 | - |
dc.identifier.issue | 10 | - |
dc.identifier.spage | 1527 | - |
dc.identifier.epage | 1544 | - |
dc.identifier.isi | WOS:000485320300008 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 0920-5691 | - |