# Learning multiview 3D point cloud registration

arXiv: https://arxiv.org/abs/2001.05119 · HTML: https://mlsanity.com/paper/2001.05119/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2020.

## Built on by (most cited first, 30 of 78)

- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://mlsanity.com/paper/2203.14517/) (2022)
- [SiLK -- Simple Learned Keypoints](https://mlsanity.com/paper/2304.06194/) (2023)
- [Deep Hough Voting for Robust Global Registration](https://mlsanity.com/paper/2109.04310/) (2021)
- [HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration](https://mlsanity.com/paper/2107.11992/) (2021)
- [Graspness Discovery in Clutters for Fast and Accurate Grasp Detection](https://mlsanity.com/paper/2406.11142/) (2024)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://mlsanity.com/paper/2102.11870/) (2021)
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://mlsanity.com/paper/2103.01055/) (2021)
- [Tangent Space Backpropagation for 3D Transformation Groups](https://mlsanity.com/paper/2103.12032/) (2021)
- [Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion](https://mlsanity.com/paper/2103.16690/) (2021)
- [Quantum Permutation Synchronization](https://mlsanity.com/paper/2101.07755/) (2021)
- [Projective Manifold Gradient Layer for Deep Rotation Regression](https://mlsanity.com/paper/2110.11657/) (2021)
- [Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization](https://mlsanity.com/paper/2111.12878/) (2021)
- [Bootstrap Your Own Correspondences](https://mlsanity.com/paper/2106.00677/) (2021)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [Dual Transformer for Point Cloud Analysis](https://mlsanity.com/paper/2104.13044/) (2021)
- [OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds](https://mlsanity.com/paper/2210.04458/) (2022)
- [HARA: A Hierarchical Approach for Robust Rotation Averaging](https://mlsanity.com/paper/2111.08831/) (2021)
- [PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds](https://mlsanity.com/paper/2110.01269/) (2021)
- [Reliable Inlier Evaluation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2202.11292/) (2022)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting](https://mlsanity.com/paper/2304.00467/) (2023)
- [ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs](https://mlsanity.com/paper/2207.00826/) (2022)
- [FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering](https://mlsanity.com/paper/2203.15765/) (2022)
- [KISS-Matcher: Fast and Robust Point Cloud Registration Revisited](https://mlsanity.com/paper/2409.15615/) (2024)
- [Point Cloud Learning with Transformer](https://mlsanity.com/paper/2104.13636/) (2021)
- [Learning Iterative Robust Transformation Synchronization](https://mlsanity.com/paper/2111.00728/) (2021)
- [DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization](https://mlsanity.com/paper/2212.06331/) (2022)

## Abstract (arXiv)

We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise alignment and the globally consistent refinement. The former is often ambiguous due to the low overlap of neighboring point clouds, symmetries and repetitive scene parts. Therefore, the latter global refinement aims at establishing the cyclic consistency across multiple scans and helps in resolving the ambiguous cases. In this paper we propose, to the best of our knowledge, the first end-to-end algorithm for joint learning of both parts of this two-stage problem. Experimental evaluation on well accepted benchmark datasets shows that our approach outperforms the state-of-the-art by a significant margin, while being end-to-end trainable and computationally less costly. Moreover, we present detailed analysis and an ablation study that validate the novel components of our approach. The source code and pretrained models are publicly available under https://github.com/zgojcic/3D_multiview_reg.