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

09/20/2022
by   Haoyi Xiu, et al.
0

3D point clouds can flexibly represent continuous surfaces and can be used for various applications; however, the lack of structural information makes point cloud recognition challenging. Recent edge-aware methods mainly use edge information as an extra feature that describes local structures to facilitate learning. Although these methods show that incorporating edges into the network design is beneficial, they generally lack interpretability, making users wonder how exactly edges help. To shed light on this issue, in this study, we propose the Diffusion Unit (DU) that handles edges in an interpretable manner while providing decent improvement. Our method is interpretable in three ways. First, we theoretically show that DU learns to perform task-beneficial edge enhancement and suppression. Second, we experimentally observe and verify the edge enhancement and suppression behavior. Third, we empirically demonstrate that this behavior contributes to performance improvement. Extensive experiments performed on challenging benchmarks verify the superiority of DU in terms of both interpretability and performance gain. Specifically, our method achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentation using S3DIS. Our source code will be released at https://github.com/martianxiu/DiffusionUnit.

READ FULL TEXT

page 1

page 2

page 5

page 6

page 7

page 8

research
07/04/2022

Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding

Learning point clouds is challenging due to the lack of connectivity inf...
research
04/07/2021

FatNet: A Feature-attentive Network for 3D Point Cloud Processing

The application of deep learning to 3D point clouds is challenging due t...
research
03/10/2022

Contrastive Boundary Learning for Point Cloud Segmentation

Point cloud segmentation is fundamental in understanding 3D environments...
research
03/03/2020

Unsupervised Learning of Intrinsic Structural Representation Points

Learning structures of 3D shapes is a fundamental problem in the field o...
research
12/12/2019

LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices

Deep convolutional neural networks (CNNs) have shown outstanding perform...
research
08/09/2021

LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Lattices

Deep convolutional neural networks (CNNs) have shown outstanding perform...
research
03/29/2023

NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud

Extracting parametric edge curves from point clouds is a fundamental pro...

Please sign up or login with your details

Forgot password? Click here to reset