# A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds

arXiv: https://arxiv.org/abs/2203.04232 · HTML: https://mlsanity.com/paper/2203.04232/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 57 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net](https://mlsanity.com/paper/2012.12395/) (2020)
- [Deeper and Wider Siamese Networks for Real-Time Visual Tracking](https://mlsanity.com/paper/1901.01660/) (2019)
- [GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning](https://mlsanity.com/paper/2006.07327/) (2020)
- [P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds](https://mlsanity.com/paper/2005.13888/) (2020)
- [The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes](https://mlsanity.com/paper/1903.01568/) (2019)
- [Joint Monocular 3D Vehicle Detection and Tracking](https://mlsanity.com/paper/1811.10742/) (2018)
- [Learning the Model Update for Siamese Trackers](https://mlsanity.com/paper/1908.00855/) (2019)
- [Leveraging Shape Completion for 3D Siamese Tracking](https://mlsanity.com/paper/1903.01784/) (2019)
- [SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition](https://mlsanity.com/paper/2011.12430/) (2020)
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2108.04728/) (2021)
- [Learning Dynamic Memory Networks for Object Tracking](https://mlsanity.com/paper/1803.07268/) (2018)
- [PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2108.06455/) (2021)
- [Robust Multi-Modality Multi-Object Tracking](https://mlsanity.com/paper/1909.03850/) (2019)
- [3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud](https://mlsanity.com/paper/2108.05630/) (2021)
- [Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters](https://mlsanity.com/paper/1811.10863/) (2018)
- [Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filtering](https://mlsanity.com/paper/1802.09975/) (2018)
- [Combined Image- and World-Space Tracking in Traffic Scenes](https://mlsanity.com/paper/1809.07357/) (2018)
- [ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion](https://mlsanity.com/paper/2104.09587/) (2021)
- [Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking](https://mlsanity.com/paper/2101.12159/) (2021)
- [SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World](https://mlsanity.com/paper/2110.12715/) (2021)
- [Efficient Bird Eye View Proposals for 3D Siamese Tracking](https://mlsanity.com/paper/1903.10168/) (2019)
- [VPC-Net: Completion of 3D Vehicles from MLS Point Clouds](https://mlsanity.com/paper/2008.03404/) (2020)

## Built on by (most cited first, 23 of 23)

- [TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer](https://mlsanity.com/paper/2211.10705/) (2022)
- [Text2Loc: 3D Point Cloud Localization from Natural Language](https://mlsanity.com/paper/2311.15977/) (2023)
- [Scalable Video Object Segmentation with Simplified Framework](https://mlsanity.com/paper/2308.09903/) (2023)
- [DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks](https://mlsanity.com/paper/2304.00571/) (2023)
- [Towards Category Unification of 3D Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2401.11204/) (2024)
- [MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues](https://mlsanity.com/paper/2412.02734/) (2024)
- [FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking](https://mlsanity.com/paper/2602.24133/) (2026)
- [Efficient and Deterministic Search Strategy Based on Residual Projections for Point Cloud Registration with Correspondences](https://mlsanity.com/paper/2305.11716/) (2023)
- [VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition](https://mlsanity.com/paper/2403.14594/) (2024)
- [Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking](https://mlsanity.com/paper/2509.11453/) (2025)
- [SCP: Scene Completion Pre-training for 3D Object Detection](https://mlsanity.com/paper/2309.06199/) (2023)
- [Anyview: Generalizable Indoor 3D Object Detection with Variable Frames](https://mlsanity.com/paper/2310.05346/) (2023)
- [BirdNeRF: Fast Neural Reconstruction of Large-Scale Scenes From Aerial Imagery](https://mlsanity.com/paper/2402.04554/) (2024)
- [FlowTrack: Point-level Flow Network for 3D Single Object Tracking](https://mlsanity.com/paper/2407.01959/) (2024)
- [Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences](https://mlsanity.com/paper/2409.04390/) (2024)
- [TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes](https://mlsanity.com/paper/2412.10308/) (2024)
- [MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models](https://mlsanity.com/paper/2503.13743/) (2025)
- [TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking](https://mlsanity.com/paper/2609.07738/) (2026)
- [RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning](https://mlsanity.com/paper/2504.12167/) (2025)
- [EasyTrack: Efficient and Compact One-stream 3D Point Clouds Tracker](https://mlsanity.com/paper/2404.05960/) (2024)
- [MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation](https://mlsanity.com/paper/2511.15077/) (2025)
- [Text2Loc++: Generalizing 3D Point Cloud Localization from Natural Language](https://mlsanity.com/paper/2511.15308/) (2025)
- [SAVTrack: Selective Vote Aggregation for Reliability-Aware Point Cloud Tracking](https://mlsanity.com/paper/2609.16662/) (2026)

## Abstract (arXiv)

Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking. However, it is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. In this paper, we address this issue by explicitly leveraging temporal motion cues and propose DMT, a Detector-free Motion-prediction-based 3D Tracking network that completely removes the usage of complicated 3D detectors and is lighter, faster, and more accurate than previous trackers. Specifically, the motion prediction module is first introduced to estimate a potential target center of the current frame in a point-cloud-free manner. Then, an explicit voting module is proposed to directly regress the 3D box from the estimated target center. Extensive experiments on KITTI and NuScenes datasets demonstrate that our DMT can still achieve better performance (~10% improvement over the NuScenes dataset) and a faster tracking speed (i.e., 72 FPS) than state-of-the-art approaches without applying any complicated 3D detectors. Our code is released at urlhttps://github.com/jimmy-dq/DMT