DeepAI AI Chat
Log In Sign Up

Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

by   Junming Zhang, et al.

Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is non-trivial due to the inability of these methods to generalize to unseen rotations. To address this limitation, one usually has to augment the training data, which can lead to extra computation and require larger model complexity. This paper proposes a new neural network called the Aligned Edge Convolutional Neural Network (AECNN) that learns a feature representation of point clouds relative to Local Reference Frames (LRFs) to ensure invariance to rotation. In particular, features are learned locally and aligned with respect to the LRF of an automatically computed reference point. The proposed approach is evaluated on point cloud classification and part segmentation tasks. This paper illustrates that the proposed technique outperforms a variety of state of the art approaches (even those trained on augmented datasets) in terms of robustness to rotation without requiring any additional data augmentation.


Point Set Voting for Partial Point Cloud Analysis

The continual improvement of 3D sensors has driven the development of al...

The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

We propose 3DSmoothNet, a full workflow to match 3D point clouds with a ...

Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

Recent progresses in 3D deep learning has shown that it is possible to d...

S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification

Many point cloud classification methods are developed under the assumpti...

Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data

In this paper, we demonstrate an end-to-end spatiotemporal gesture learn...

Effective Early Stopping of Point Cloud Neural Networks

Early stopping techniques can be utilized to decrease the time cost, how...

Point-cloud-based place recognition using CNN feature extraction

This paper proposes a novel point-cloud-based place recognition system t...