BPNet: Bézier Primitive Segmentation on 3D Point Clouds

by   Rao Fu, et al.
The University of Sydney
Shanghai Jiao Tong University

This paper proposes BPNet, a novel end-to-end deep learning framework to learn Bézier primitive segmentation on 3D point clouds. The existing works treat different primitive types separately, thus limiting them to finite shape categories. To address this issue, we seek a generalized primitive segmentation on point clouds. Taking inspiration from Bézier decomposition on NURBS models, we transfer it to guide point cloud segmentation casting off primitive types. A joint optimization framework is proposed to learn Bézier primitive segmentation and geometric fitting simultaneously on a cascaded architecture. Specifically, we introduce a soft voting regularizer to improve primitive segmentation and propose an auto-weight embedding module to cluster point features, making the network more robust and generic. We also introduce a reconstruction module where we successfully process multiple CAD models with different primitives simultaneously. We conducted extensive experiments on the synthetic ABC dataset and real-scan datasets to validate and compare our approach with different baseline methods. Experiments show superior performance over previous work in terms of segmentation, with a substantially faster inference speed.


page 3

page 6

page 7


Fit4CAD: A point cloud benchmark for fitting simple geometric primitives in CAD objects

We propose Fit4CAD, a benchmark for the evaluation and comparison of met...

HPNet: Deep Primitive Segmentation Using Hybrid Representations

This paper introduces HPNet, a novel deep-learning approach for segmenti...

Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits

We present a novel and effective method for detecting 3D primitives in c...

User-guided free-form asset modelling

In this paper a new system for piecewise primitive surface recovery on p...

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

We propose a new method for segmentation-free joint estimation of orthog...

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

This paper presents a fully automatic framework for extracting editable ...

A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds

This paper proposes a segmentation-free, automatic and efficient procedu...

Please sign up or login with your details

Forgot password? Click here to reset