Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme

2021-03-10 · Jean-Baptiste Weibel, Timothy Patten, Markus Vincze

While object semantic understanding is essential for most service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem, but most methods still struggle with the differences existing between artificial and real 3D data. We conjecture that the cause of those issue is the fact that many methods learn directly from point coordinates, instead of the shape, as the former is hard to center and to scale under variable occlusions reliably. We introduce spherical kernel point convolutions that directly exploit the object surface, represented as a graph, and a voting scheme to limit the impact of poor segmentation on the classification results. Our proposed approach improves upon state-of-the-art methods by up to 36% when transferring from artificial objects to real objects.

📄 PDF Abstract BibTeX arXiv:2103.06134

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object Classification General ClassificationObject

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Spherical Convolutional Neural Network for 3D Point Clouds

2018-05-21 · Huan Lei, Naveed Akhtar, Ajmal Mian

We propose a neural network for 3D point cloud processing that exploits `spherical' convolution kernels and octree partitioning of space. The proposed metric-based spherical kernels systematically quantize point neighbor…

3D Object Classification General Classification Translation

Octree guided CNN with Spherical Kernels for 3D Point Clouds

2019-02-28 · CVPR 2019 6 · Huan Lei, Naveed Akhtar, Ajmal Mian

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point…

3D Object Classification 3D Part Segmentation Translation

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

2019-09-20 · Huan Lei, Naveed Akhtar, Ajmal Mian

We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar t…

3D Instance Segmentation 3D Object Classification 3D Part Segmentation Point Cloud Classification+2

Effective Rotation-invariant Point CNN with Spherical Harmonics kernels

2019-06-27 · Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, Maks Ovsjanikov

We present a novel rotation invariant architecture operating directly on point cloud data. We demonstrate how rotation invariance can be injected into a recently proposed point-based PCNN architecture, at all layers of t…

Data Augmentation

E2PN: Efficient SE(3)-Equivariant Point Network

2022-06-11 · CVPR 2023 1 · Minghan Zhu, Maani Ghaffari, William A. Clark, Huei Peng

This paper proposes a convolution structure for learning SE(3)-equivariant features from 3D point clouds. It can be viewed as an equivariant version of kernel point convolutions (KPConv), a widely used convolution form t…

Pose Estimation