Adversarial Unsupervised Domain Adaptation for 3D Semantic Segmentation with 2D Image Fusion of Dense Depth

Simple item page
dc.contributor.authorZhang, Xindanen_US
dc.contributor.authorLi, Yingen_US
dc.contributor.authorSheng, Huankunen_US
dc.contributor.authorZhang, Xinnianen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:09:30Z
dc.date.available2024-10-13T18:09:30Z
dc.date.issued2024
dc.description.abstractUnsupervised domain adaptation (UDA) is increasingly used for 3D point cloud semantic segmentation tasks due to its ability to address the issue of missing labels for new domains. However, most existing unsupervised domain adaptation methods focus only on uni-modal data and are rarely applied to multi-modal data. Therefore, we propose a cross-modal UDA on multimodal datasets that contain 3D point clouds and 2D images for 3D Semantic Segmentation. Specifically, we first propose a Dual discriminator-based Domain Adaptation (Dd-bDA) module to enhance the adaptability of different domains. Second, given that the robustness of depth information to domain shifts can provide more details for semantic segmentation, we further employ a Dense depth Feature Fusion (DdFF) module to extract image features with rich depth cues. We evaluate our model in four unsupervised domain adaptation scenarios, i.e., dataset-to-dataset (A2D2→SemanticKITTI), Day-to-Night, country-tocountry (USA→Singapore), and synthetic-to-real (VirtualKITTI→SemanticKITTI). In all settings, the experimental results achieve significant improvements and surpass state-of-the-art models.en_US
dc.description.number7
dc.description.sectionheadersImage Processing and Filtering II
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15250
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15250
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15250
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Point-based models
dc.subjectComputing methodologies → Point
dc.subjectbased models
dc.titleAdversarial Unsupervised Domain Adaptation for 3D Semantic Segmentation with 2D Image Fusion of Dense Depthen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
cgf15250.pdf
Size:
15.76 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 7