Timezone: »

 
Poster
PIE-NET: Parametric Inference of Point Cloud Edges
Xiaogang Wang · Yuelang Xu · Kai Xu · Andrea Tagliasacchi · Bin Zhou · Ali Mahdavi-Amiri · Hao Zhang

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #476
in Poster Session 2 »

We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,~lines, circles, and B-splines). Accordingly, our deep neural network, coined PIE-NET, is trained for parametric inference of edges. The network relies on a "region proposal" architecture, where a first module proposes an over-complete collection of edge and corner points, and a second module ranks each proposal to decide whether it should be considered. We train and evaluate our method on the ABC dataset, a large dataset of CAD models, and compare our results to those produced by traditional (non-learning) processing pipelines, as well as a recent deep learning based edge detector (EC-NET). Our results significantly improve over the state-of-the-art from both a quantitative and qualitative standpoint.

Keywords: Fairness, Accountability, and Transparency · Game Theory and Computational Economics · Applications · Theory

Author Information

Xiaogang Wang (Beihang University)
Yuelang Xu (Tsinghua University)
Kai Xu (National University of Defense Technology)
Andrea Tagliasacchi (Google Research, Brain)
Bin Zhou (State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering,Beihang University)
Ali Mahdavi-Amiri (Simon Fraser University)
Hao Zhang (Simon Fraser University)

More from the Same Authors