CVDec 22, 2020

Robust Kernel-based Feature Representation for 3D Point Cloud Analysis via Circular Convolutional Network

arXiv:2012.12215v56 citations
Originality Highly original
AI Analysis

This work addresses the challenge of creating rotation and scale-invariant descriptors for 3D point cloud analysis, which is a critical problem for applications like registration and segmentation in real-world scenarios.

This paper introduces a new local feature description method for 3D point clouds that is robust to rotation, density, and scale variations. The method significantly improved registration performance on benchmark datasets, reducing rotation and translation errors by 70% compared to state-of-the-art methods, while achieving comparable results in classification and part segmentation.

Feature descriptors of point clouds are used in several applications, such as registration and part segmentation of 3D point clouds. Learning discriminative representations of local geometric features is unquestionably the most important task for accurate point cloud analyses. However, it is challenging to develop rotation or scale-invariant descriptors. Most previous studies have either ignored rotations or empirically studied optimal scale parameters, which hinders the applicability of the methods for real-world datasets. In this paper, we present a new local feature description method that is robust to rotation, density, and scale variations. Moreover, to improve representations of the local descriptors, we propose a global aggregation method. First, we place kernels aligned around each point in the normal direction. To avoid the sign problem of the normal vector, we use a symmetric kernel point distribution in the tangential plane. From each kernel point, we first projected the points from the spatial space to the feature space, which is robust to multiple scales and rotation, based on angles and distances. Subsequently, we perform graph convolutions by considering local kernel point structures and long-range global context, obtained by a global aggregation method. We experimented with our proposed descriptors on benchmark datasets (i.e., ModelNet40 and ShapeNetPart) to evaluate the performance of registration, classification, and part segmentation on 3D point clouds. Our method showed superior performances when compared to the state-of-the-art methods by reducing 70$\%$ of the rotation and translation errors in the registration task. Our method also showed comparable performance in the classification and part-segmentation tasks with simple and low-dimensional architectures.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes