# PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

arXiv: https://arxiv.org/abs/2407.10142 · HTML: https://mlsanity.com/paper/2407.10142/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 14 Jul 2024.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors](https://mlsanity.com/paper/2109.00182/) (2021)
- [SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration](https://mlsanity.com/paper/2203.14453/) (2022)

## Built on by (most cited first, 18 of 18)

- [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://mlsanity.com/paper/2512.01850/) (2025)
- [BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes](https://mlsanity.com/paper/2503.07940/) (2025)
- [Unlocking Generalization Power in LiDAR Point Cloud Registration](https://mlsanity.com/paper/2503.10149/) (2025)
- [Combinative Matching for Geometric Shape Assembly](https://mlsanity.com/paper/2508.09780/) (2025)
- [FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)N Diffusion Refinement](https://mlsanity.com/paper/2512.09373/) (2025)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration](https://mlsanity.com/paper/2503.17093/) (2025)
- [Toward Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups](https://mlsanity.com/paper/2601.02759/) (2026)
- [iMatcher: Improve matching in point cloud registration via local-to-global geometric consistency learning](https://mlsanity.com/paper/2509.08982/) (2025)
- [Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context](https://mlsanity.com/paper/2509.24275/) (2025)
- [ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance](https://mlsanity.com/paper/2511.22908/) (2025)
- [Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration](https://mlsanity.com/paper/2512.09407/) (2025)
- [R3PM-Net: Real-time, Robust, Real-world Point Matching Network](https://mlsanity.com/paper/2604.05060/) (2026)
- [From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generation](https://mlsanity.com/paper/2606.27412/) (2026)
- [Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations](https://mlsanity.com/paper/2607.00498/) (2026)
- [Test Time Adaptation Methods for Point Cloud Registration in Laparoscopic Surgery](https://mlsanity.com/paper/2608.02883/) (2026)
- [BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration](https://mlsanity.com/paper/2609.11472/) (2026)
- [Levy-Driven Correspondence Estimation for Registration](https://mlsanity.com/paper/2609.32612/) (2026)

## Abstract (arXiv)

Learning rotation-invariant distinctive features is a fundamental requirement for point cloud registration. Existing methods often use rotation-sensitive networks to extract features, while employing rotation augmentation to learn an approximate invariant mapping rudely. This makes networks fragile to rotations, overweight, and hinders the distinctiveness of features. To tackle these problems, we propose a novel position-aware rotation-equivariant network, for efficient, light-weighted, and robust registration. The network can provide a strong model inductive bias to learn rotation-equivariant/invariant features, thus addressing the aforementioned limitations. To further improve the distinctiveness of descriptors, we propose a position-aware convolution, which can better learn spatial information of local structures. Moreover, we also propose a feature-based hypothesis proposer. It leverages rotation-equivariant features that encode fine-grained structure orientations to generate reliable model hypotheses. Each correspondence can generate a hypothesis, thus it is more efficient than classic estimators that require multiple reliable correspondences. Accordingly, a contrastive rotation loss is presented to enhance the robustness of rotation-equivariant features against data degradation. Extensive experiments on indoor and outdoor datasets demonstrate that our method significantly outperforms the SOTA methods in terms of registration recall while being lightweight and keeping a fast speed. Moreover, experiments on rotated datasets demonstrate its robustness against rotation variations. Code is available at https://github.com/yaorz97/PARENet.