Resolution-switchable 3D Semantic Scene Completion

Simple item page
dc.contributor.authorLuo, Shoutongen_US
dc.contributor.authorSun, Zhengxingen_US
dc.contributor.authorSun, Yunhanen_US
dc.contributor.authorWang, Yien_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:39:34Z
dc.date.available2022-10-04T06:39:34Z
dc.date.issued2022
dc.description.abstractSemantic scene completion (SSC) aims to recover the complete geometric structure as well as the semantic segmentation results from partial observations. Previous works could only perform this task at a fixed resolution. To handle this problem, we propose a new method that can generate results at different resolutions without redesigning and retraining. The basic idea is to decouple the direct connection between resolution and network structure. To achieve this, we convert feature volume generated by SSC encoders into a resolution adaptive feature and decode this feature via point. We also design a resolution-adapted point sampling strategy for testing and a category-based point sampling strategy for training to further handle this problem. The encoder of our method can be replaced by existing SSC encoders. We can achieve better results at other resolutions while maintaining the same accuracy as the original resolution results. Code and data are available at https://github.com/lstcutong/ReS-SSC.en_US
dc.description.number7
dc.description.sectionheadersPoint Cloud Generation
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14662
dc.identifier.issn1467-8659
dc.identifier.pages121-130
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14662
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14662
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Volumetric models
dc.subjectComputing methodologies → Volumetric models
dc.titleResolution-switchable 3D Semantic Scene Completionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp121-130.pdf
Size:
3.99 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7