TopoGen: Topology-Aware 3D Generation with Persistence Points

Simple item page
dc.contributor.authorHu, Jiangbeien_US
dc.contributor.authorFei, Benen_US
dc.contributor.authorXu, Baixinen_US
dc.contributor.authorHou, Feien_US
dc.contributor.authorWang, Shengfaen_US
dc.contributor.authorLei, Naen_US
dc.contributor.authorYang, Weidongen_US
dc.contributor.authorQian, Chenen_US
dc.contributor.authorHe, Yingen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:02:51Z
dc.date.available2025-10-07T05:02:51Z
dc.date.issued2025
dc.description.abstractTopological properties play a crucial role in the analysis, reconstruction, and generation of 3D shapes. Yet, most existing research focuses primarily on geometric features, due to the lack of effective representations for topology. In this paper, we introduce TopoGen, a method that extracts both discrete and continuous topological descriptors-Betti numbers and persistence points-using persistent homology. These features provide robust characterizations of 3D shapes in terms of their topology. We incorporate them as conditional guidance in generative models for 3D shape synthesis, enabling topology-aware generation from diverse inputs such as sparse and partial point clouds, as well as sketches. Furthermore, by modifying persistence points, we can explicitly control and alter the topology of generated shapes. Experimental results demonstrate that TopoGen enhances both diversity and controllability in 3D generation by embedding global topological structure into the synthesis process.en_US
dc.description.number7
dc.description.sectionheadersSynthetizing 3D shapes
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70257
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70257
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70257
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Shape modeling; Artificial intelligence
dc.subjectComputing methodologies → Shape modeling
dc.subjectArtificial intelligence
dc.titleTopoGen: Topology-Aware 3D Generation with Persistence Pointsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70257.pdf
Size:
38.48 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 7