GERA: Geometric Embedding for Efficient Point Registration Analysis
Not on the map. Why?
Abstract (arXiv)
Point cloud registration aims to provide estimated transformations to align point clouds, which plays a crucial role in pose estimation of various navigation systems, such as surgical guidance systems and autonomous vehicles. Despite the impressive performance of recent models on benchmark datasets, many rely on complex modules like KPConv and Transformers, which impose significant computational and memory demands. These requirements hinder their practical application, particularly in resource-constrained environments such as mobile robotics. In this paper, we propose a novel point cloud registration network that leverages a pure MLP architecture, constructing geometric information offline. This approach eliminates the computational and memory burdens associated with traditional complex feature extractors and significantly reduces inference time and resource consumption. Our method is the first to replace 3D coordinate inputs with offline-constructed geometric encoding, improving generalization and stability, as demonstrated by Maximum Mean Discrepancy (MMD) comparisons. This efficient and accurate geometric representation marks a significant advancement in point cloud analysis, particularly for applications requiring fast and reliability.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 1 Oct 2024.
Builds on
23 of 40 references.
References · 23
- 2017Attention Is All You Needcited by 60,361
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
- 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
- 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
- 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 151
- 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
- 2021LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAMcited by 67
- 2021Point-set Distances for Learning Representations of 3D Point Cloudscited by 48
- 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
11 more
- 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
- 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Visioncited by 32
- 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
- 2021Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapterscited by 21
- 2024GaussReg: Fast 3D Registration with Gaussian Splattingcited by 19
- 2023Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAMcited by 18
- 2023MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentationcited by 17
- 2023Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?cited by 14
- 2021Real-time multimodal image registration with partial intraoperative point-set datacited by 10
- 2024Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysiscited by 10
- 2023Comparing Regularized Kelvinlet Functions and the Finite Element Method for Registration of Medical Images to Sparse Organ Datacited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.