Xianghao Xu — accepted AI-conference papers

2023

Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly

Xianghao Xu, Paul Guerrero, Matthew Fisher, Siddhartha Chaudhuri, Daniel Ritchie

CVPR 2023poster

Representing a 3D shape with a set of primitives can aid perception of structure, improve robotic object manipulation, and enable editing, stylization, and compression of 3D shapes. Existing methods either use simple parametric primitives or learn a generative shape space of parts. Both have limitat…

Cited by 13 Source ↗PDF ↗Scholar ↗

2021

Inferring CAD Modeling Sequences Using Zone Graphs

Xianghao Xu, Wenzhe Peng, Chin-Yi Cheng, Karl D.D. Willis, Daniel Ritchie

CVPR 2021poster

In computer-aided design (CAD), the ability to "reverse engineer" the modeling steps used to create 3D shapes is a long-sought-after goal. This process can be decomposed into two sub-problems: converting an input mesh or point cloud into a boundary representation (or B-rep), and then inferring model…

Cited by 75 PDF ↗code ↗Scholar ↗