Presentation

<
Part123: Part-aware 3D Reconstruction From a Single-view Image
SessionGeometry: Reconstruction
DescriptionThis paper proposes Part123, a novel framework for part-aware 3D reconstruction from a single-view image. Based on the multiview images generated by multiview diffusion, we apply contrastive learning to incorporate their 2D image segmentations into the 3D reconstruction process, thus enabling the generation of 3D models with high-quality part segments.
Authors
Anran Liu
University of Hong Kong
Cheng Lin
University of Hong Kong
Yuan Liu
University of Hong Kong
Xiaoxiao Long
University of Hong Kong
Zhiyang Dou
University of Hong Kong
Hao-Xiang Guo
Tsinghua University
Ping Luo
University of Hong Kong
Wenping Wang
Texas A&M University
Event Type
Technical Paper
TimeMonday, 29 July 20242:40pm - 2:50pm MDT
LocationMile High 2A
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 20242:00pm - 3:30pm MDTMile High 2A
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Geometry
Modeling
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationNeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvature