Concentric Spherical GNN for 3D Representation Learning

ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics

Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data. While being able to achieve good accuracies in various scene understanding tasks, previous methods often have low training speed and complex network architecture. In this paper, we address these problems by proposing an efficient end-to-end permutation invariant convolution for point cloud deep learning. Our simple yet effective convolution operator named ShellConv uses statistics from concentric spherical shells to define re…

Robust Object Classification Approach using Spherical Harmonics

In this paper, we present a robust spherical harmonics approach for the classification of point cloud-based objects. Spherical harmonics have been used for classification over the years, with several frameworks existing in the literature. These approaches use variety of spherical harmonics based descriptors to classify objects. We first investigated these frameworks robustness against data augmentation, such as outliers and noise, as it has not been studied before. Then we propose a spherical convolution neural network framework for robust object classification. The proposed framework uses the…

Spotlights: Probing Shapes from Spherical Viewpoints

Recent years have witnessed the surge of learned representations that directly build upon point clouds. Though becoming increasingly expressive, most existing representations still struggle to generate ordered point sets. Inspired by spherical multi-view scanners, we propose a novel sampling model called Spotlights to represent a 3D shape as a compact 1D array of depth values. It simulates the configuration of cameras evenly distributed on a sphere, where each virtual camera casts light rays from its principal point through sample points on a small concentric spherical cap to probe for the pos…

Graph-CoVis：基于GNN的多视图全景图全局位姿估计

Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation

针对直立假设下360°全景图宽基线全局位姿估计问题，提出基于GNN的Graph-CoVis框架，将两视图相对位姿回归扩展为多视图全局估计，在ZInD数据集上达到与SOTA相当的性能。

QSV：四元数-球面-视觉，用于球面格上的耦合四元数注意力

QSV: Quat-Sphere-Vision for Coupled Quaternion Attention on Spherical Lattices

QSV用单位四元数耦合注意力与特征传输，在球面格上稀疏kNN图传递消息，消融显示传输主导学习，但几何本身不如标准注意力。

用于高效分子建模的等变球形 Transformer

Equivariant Spherical Transformer for Efficient Molecular Modeling

本文提出即插即用的 Equivariant Spherical Transformer，在群表示 Fourier 空间域引入 Transformer 并保持等变归纳偏置，在 OC20、QM9 上达到最先进性能并验证其等变性。