# Any Motion Detector: Learning Class-agnostic Scene Dynamics from a Sequence of LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2004.11647 · HTML: https://mlsanity.com/paper/2004.11647/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://mlsanity.com/paper/2104.08683/) (2021)
- [TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving](https://mlsanity.com/paper/2303.09998/) (2023)
- [Instantaneous Perception of Moving Objects in 3D](https://mlsanity.com/paper/2405.02781/) (2024)
- [Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior](https://mlsanity.com/paper/2310.11284/) (2023)
- [TimePillars: Temporally-Recurrent 3D LiDAR Object Detection](https://mlsanity.com/paper/2312.17260/) (2023)
- [Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving](https://mlsanity.com/paper/2509.13116/) (2025)

## Abstract (arXiv)

Object detection and motion parameters estimation are crucial tasks for self-driving vehicle safe navigation in a complex urban environment. In this work we propose a novel real-time approach of temporal context aggregation for motion detection and motion parameters estimation based on 3D point cloud sequence. We introduce an ego-motion compensation layer to achieve real-time inference with performance comparable to a naive odometric transform of the original point cloud sequence. Not only is the proposed architecture capable of estimating the motion of common road participants like vehicles or pedestrians but also generalizes to other object categories which are not present in training data. We also conduct an in-deep analysis of different temporal context aggregation strategies such as recurrent cells and 3D convolutions. Finally, we provide comparison results of our state-of-the-art model with existing solutions on KITTI Scene Flow dataset.