File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Anisotropic convolutional networks for 3D semantic scene completion

TitleAnisotropic convolutional networks for 3D semantic scene completion
Authors
Issue Date2020
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, p. 3348-3356 How to Cite?
AbstractAs a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely. The basic idea is to enable anisotropic 3D receptive field by decomposing a 3D convolution into three consecutive 1D convolutions, and the kernel size for each such 1D convolution is adaptively determined on the fly. By stacking multiple such anisotropic convolution modules, the voxel-wise modeling capability can be further enhanced while maintaining a controllable amount of model parameters. Extensive experiments on two SSC benchmarks, NYU-Depth-v2 and NYUCAD, show the superior performance of the proposed method. Our code is available at https://waterljwant.github.io/SSC/.
Persistent Identifierhttp://hdl.handle.net/10722/311497
ISSN
2020 SCImago Journal Rankings: 4.658

 

DC FieldValueLanguage
dc.contributor.authorLi, Jie-
dc.contributor.authorHan, Kai-
dc.contributor.authorWang, Peng-
dc.contributor.authorLiu, Yu-
dc.contributor.authorYuan, Xia-
dc.date.accessioned2022-03-22T11:54:05Z-
dc.date.available2022-03-22T11:54:05Z-
dc.date.issued2020-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, p. 3348-3356-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/311497-
dc.description.abstractAs a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely. The basic idea is to enable anisotropic 3D receptive field by decomposing a 3D convolution into three consecutive 1D convolutions, and the kernel size for each such 1D convolution is adaptively determined on the fly. By stacking multiple such anisotropic convolution modules, the voxel-wise modeling capability can be further enhanced while maintaining a controllable amount of model parameters. Extensive experiments on two SSC benchmarks, NYU-Depth-v2 and NYUCAD, show the superior performance of the proposed method. Our code is available at https://waterljwant.github.io/SSC/.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleAnisotropic convolutional networks for 3D semantic scene completion-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR42600.2020.00341-
dc.identifier.scopuseid_2-s2.0-85094162301-
dc.identifier.spage3348-
dc.identifier.epage3356-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats