Presentation

<
Autoregressive B-Rep Shape Generation with Parametric Surfaces
SessionLearning for CAD
DescriptionParaCAD is a point-cloud-conditioned autoregressive framework for B-Rep generation that directly predicts native parametric surface types and continuous parameters via a surface-centric tokenization, preserving CAD semantics and downstream editability beyond grid/point-based representations.
Authors
Dafei Qin
University of Hong Kong
Rui Xu
University of Hong Kong
Zeyu Shen
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Kaichun Qiao
ShanghaiTech University
Hongyang Lin
ShanghaiTech University
Qixuan Zhang
ShanghaiTech University
Huaijin Pi
University of Hong Kong
Lan Xu
ShanghaiTech University
Jingyi Yu
ShanghaiTech University
Wenping Wang
Texas A&M University
Taku Komura
University of Hong Kong
Event Type
Technical Paper
TimeMonday, 20 July 202610:55am - 11:05am PDT
LocationRoom 403 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Monday, 20 July 202610:45am - 12:15pm PDTRoom 403 B
Keywords
Artificial Intelligence/Machine Learning
Modeling
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationB-repLer: Language-guided Editing of CAD Models
Similar Presentations
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
DualBrep: A Dual-Field Continuous Representation for B-rep Modelling
Flatten the Complex: Joint B-Rep Generation via Compositional k-Cell Particles