# AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects

arXiv: https://arxiv.org/abs/1910.04668 · HTML: https://mlsanity.com/paper/1910.04668/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [A comprehensive survey on point cloud registration](https://mlsanity.com/paper/2103.02690/) (2021)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences](https://mlsanity.com/paper/2103.06028/) (2021)
- [SeMoLi: What Moves Together Belongs Together](https://mlsanity.com/paper/2402.19463/) (2024)
- [RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation](https://mlsanity.com/paper/2104.05328/) (2021)
- [Towards Learning to Complete Anything in Lidar](https://mlsanity.com/paper/2504.12264/) (2025)
- [Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild](https://mlsanity.com/paper/2111.12728/) (2021)
- [Towards Class-agnostic Tracking Using Feature Decorrelation in Point Clouds](https://mlsanity.com/paper/2202.13524/) (2022)
- [(Just) A Spoonful of Refinements Helps the Registration Error Go Down](https://mlsanity.com/paper/2108.03257/) (2021)
- [A Strong Baseline for Point Cloud Registration via Direct Superpoints Matching](https://mlsanity.com/paper/2307.01362/) (2023)
- [DPCN++: Differentiable Phase Correlation Network for Versatile Pose Registration](https://mlsanity.com/paper/2206.05707/) (2022)

## Abstract (arXiv)

Methods tackling multi-object tracking need to estimate the number of targets in the sensing area as well as to estimate their continuous state. While the majority of existing methods focus on data association, precise state (3D pose) estimation is often only coarsely estimated by approximating targets with centroids or (3D) bounding boxes. However, in automotive scenarios, motion perception of surrounding agents is critical and inaccuracies in the vehicle close-range can have catastrophic consequences. In this work, we focus on precise 3D track state estimation and propose a learning-based approach for object-centric relative motion estimation of partially observed objects. Instead of approximating targets with their centroids, our approach is capable of utilizing noisy 3D point segments of objects to estimate their motion. To that end, we propose a simple, yet effective and efficient network, method, that learns to align point clouds. Our evaluation on two different datasets demonstrates that our method outperforms computationally expensive, global 3D registration methods while being significantly more efficient. We make our data, code, and models available at https://www.vision.rwth-aachen.de/page/alignnet.