File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: GAL: Geometric adversarial loss for single-view 3D-object reconstruction

TitleGAL: Geometric adversarial loss for single-view 3D-object reconstruction
Authors
KeywordsGeometric consistency
3D Neural network
3D Reconstruction
Adversarial loss
Point cloud
Issue Date2018
PublisherSpringer.
Citation
15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VIII, p. 820-834. Cham, Switzerland: Springer, 2018 How to Cite?
Abstract© Springer Nature Switzerland AG 2018. In this paper, we present a framework for reconstructing a point-based 3D model of an object from a single-view image. We found distance metrics, like Chamfer distance, were used in previous work to measure the difference of two point sets and serve as the loss function in point-based reconstruction. However, such point-point loss does not constrain the 3D model from a global perspective. We propose adding geometric adversarial loss (GAL). It is composed of two terms where the geometric loss ensures consistent shape of reconstructed 3D models close to ground-truth from different viewpoints, and the conditional adversarial loss generates a semantically-meaningful point cloud. GAL benefits predicting the obscured part of objects and maintaining geometric structure of the predicted 3D model. Both the qualitative results and quantitative analysis manifest the generality and suitability of our method.
Persistent Identifierhttp://hdl.handle.net/10722/281966
ISBN
ISSN
2005 Impact Factor: 0.402
2015 SCImago Journal Rankings: 0.252
Series/Report no.Lecture Notes in Computer Science ; 11212

 

DC FieldValueLanguage
dc.contributor.authorJiang, Li-
dc.contributor.authorShi, Shaoshuai-
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2020-04-09T09:19:15Z-
dc.date.available2020-04-09T09:19:15Z-
dc.date.issued2018-
dc.identifier.citation15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VIII, p. 820-834. Cham, Switzerland: Springer, 2018-
dc.identifier.isbn9783030012366-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/281966-
dc.description.abstract© Springer Nature Switzerland AG 2018. In this paper, we present a framework for reconstructing a point-based 3D model of an object from a single-view image. We found distance metrics, like Chamfer distance, were used in previous work to measure the difference of two point sets and serve as the loss function in point-based reconstruction. However, such point-point loss does not constrain the 3D model from a global perspective. We propose adding geometric adversarial loss (GAL). It is composed of two terms where the geometric loss ensures consistent shape of reconstructed 3D models close to ground-truth from different viewpoints, and the conditional adversarial loss generates a semantically-meaningful point cloud. GAL benefits predicting the obscured part of objects and maintaining geometric structure of the predicted 3D model. Both the qualitative results and quantitative analysis manifest the generality and suitability of our method.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofComputer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VIII-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 11212-
dc.subjectGeometric consistency-
dc.subject3D Neural network-
dc.subject3D Reconstruction-
dc.subjectAdversarial loss-
dc.subjectPoint cloud-
dc.titleGAL: Geometric adversarial loss for single-view 3D-object reconstruction-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-030-01237-3_49-
dc.identifier.scopuseid_2-s2.0-85055421032-
dc.identifier.spage820-
dc.identifier.epage834-
dc.identifier.eissn1611-3349-
dc.publisher.placeCham, Switzerland-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats