# Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution

arXiv: https://arxiv.org/abs/1811.09361 · HTML: https://mlsanity.com/paper/1811.09361/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2018.

## Built on by (most cited first, 16 of 16)

- [Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimation](https://mlsanity.com/paper/2111.00190/) (2021)
- [USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation](https://mlsanity.com/paper/2209.13864/) (2022)
- [PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features](https://mlsanity.com/paper/2102.12093/) (2021)
- [Point Cloud Learning with Transformer](https://mlsanity.com/paper/2104.13636/) (2021)
- [RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network](https://mlsanity.com/paper/2108.12790/) (2021)
- [CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame](https://mlsanity.com/paper/2303.03101/) (2023)
- [Disentangling Geometric Deformation Spaces in Generative Latent Shape Models](https://mlsanity.com/paper/2103.00142/) (2021)
- [Concentric Spherical GNN for 3D Representation Learning](https://mlsanity.com/paper/2103.10484/) (2021)
- [SN-Graph: a Minimalist 3D Object Representation for Classification](https://mlsanity.com/paper/2105.14784/) (2021)
- [Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation](https://mlsanity.com/paper/2107.03105/) (2021)
- [ML4ML: Automated Invariance Testing for Machine Learning Models](https://mlsanity.com/paper/2109.12926/) (2021)
- [General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment](https://mlsanity.com/paper/2302.09907/) (2023)
- [DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain](https://mlsanity.com/paper/2406.03017/) (2024)
- [Seeing by haptic glance: reinforcement learning-based 3D object Recognition](https://mlsanity.com/paper/2102.07599/) (2021)
- [Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimation](https://mlsanity.com/paper/2109.01397/) (2021)
- [Been There, Scanned That: Nostalgia-Driven LiDAR Compression for Self-Driving Cars](https://mlsanity.com/paper/2511.00652/) (2025)

## Abstract (arXiv)

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Pointwise Rotation-Invariant Network, focusing on rotation-invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. In addition, we propose Spherical Voxel Convolution and Point Re-sampling to extract rotation-invariant features for each point. Our network can be applied to tasks ranging from object classification, part segmentation, to 3D feature matching and label alignment. We show that, on the dataset with randomly rotated point clouds, PRIN demonstrates better performance than state-of-the-art methods without any data augmentation. We also provide theoretical analysis for the rotation-invariance achieved by our methods.