Unsupervised Learning of Intrinsic Structural Representation Points

by   Nenglun Chen, et al.

Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points. The 3D structure points pro-duced by our method encode the shape structure intrinsi-cally and exhibit semantic consistency across all the shapeinstances with similar structures. This is a challenging goal that has not fully been achieved by other methods. Specifically, our method takes a 3D point cloud as input and encodes it as a set of local features. The local features are then passed through a novel point integration module to produce a set of 3D structure points. The chamfer distance is used as reconstruction loss to ensure the structure points lie close to the input point cloud. Extensive experiments have shown that our method outperforms the state-of-the-art on the semantic shape correspondence task and achieves achieve comparable performance with state-of-the-art on the segmentation label transfer task. Moreover, the PCA based shape embedding built upon consistent structure points demonstrates good performance in preserving the shape structures. Code is available at https://github.com/NolenChen/3DStructurePoints


page 1

page 2

page 3

page 4


SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator

In this paper, we propose a novel network, SVDFormer, to tackle two spec...

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

Recently, 3D understanding research pays more attention to extracting th...

Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds

Recently deep learning has achieved significant progress on point cloud ...

Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions

Various 3D semantic attributes such as segmentation masks, geometric fea...

PointScatter: Point Set Representation for Tubular Structure Extraction

This paper explores the point set representation for tubular structure e...

Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation

3D point clouds can flexibly represent continuous surfaces and can be us...

Point Set Self-Embedding

This work presents an innovative method for point set self-embedding, th...

Please sign up or login with your details

Forgot password? Click here to reset