Presentation

<
DiffCAD: Weakly-supervised Probabilistic CAD Model Retrieval and Alignment From an RGB Image
Session3D Shape Analysis
DescriptionDiffCAD introduces probabilistic CAD retrieval and alignment to an RGB image. It models the disentangled distributions of scene scale, object pose, and shape leveraging diffusion. This enables cross-domain multi hypothesis CAD reconstruction, capturing the inherent ambiguities in depth/scale and object shape/pose, while only trained on synthetic data.
Authors
Daoyi Gao
Technical University of Munich
David Rozenberszki
Technical University of Munich
Stefan Leutenegger
Technical University of Munich
Angela Dai
Technical University of Munich
Event Type
Technical Paper
TimeWednesday, 31 July 20242:00pm - 2:10pm 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
Wednesday, 31 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
Wednesday
Next PresentationNext Presentation3Doodle: Compact Abstraction of Objects With 3D Strokes