# Correlation Pyramid Network for 3D Single Object Tracking

arXiv: https://arxiv.org/abs/2305.09195 · HTML: https://mlsanity.com/paper/2305.09195/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 16 May 2023.

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines](https://mlsanity.com/paper/1911.06188/) (2019)
- [Deeper and Wider Siamese Networks for Real-Time Visual Tracking](https://mlsanity.com/paper/1901.01660/) (2019)
- [Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking](https://mlsanity.com/paper/2203.05328/) (2022)
- [P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds](https://mlsanity.com/paper/2005.13888/) (2020)
- [Monocular Quasi-Dense 3D Object Tracking](https://mlsanity.com/paper/2103.07351/) (2021)
- [Leveraging Shape Completion for 3D Siamese Tracking](https://mlsanity.com/paper/1903.01784/) (2019)
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2108.04728/) (2021)
- [PTTR: Relational 3D Point Cloud Object Tracking with Transformer](https://mlsanity.com/paper/2112.02857/) (2021)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2108.06455/) (2021)
- [Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2203.01730/) (2022)
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://mlsanity.com/paper/2111.04426/) (2021)
- [3D Object Tracking with Transformer](https://mlsanity.com/paper/2110.14921/) (2021)
- [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)
- [3D Siamese Transformer Network for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2207.11995/) (2022)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [Efficient Bird Eye View Proposals for 3D Siamese Tracking](https://mlsanity.com/paper/1903.10168/) (2019)

## Built on by (most cited first, 10 of 10)

- [Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking](https://mlsanity.com/paper/2308.12549/) (2023)
- [TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation](https://mlsanity.com/paper/2309.07849/) (2023)
- [P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds](https://mlsanity.com/paper/2407.05238/) (2024)
- [CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking](https://mlsanity.com/paper/2511.15580/) (2025)
- [VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking](https://mlsanity.com/paper/2408.02263/) (2024)
- [TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking](https://mlsanity.com/paper/2507.19908/) (2025)
- [TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking](https://mlsanity.com/paper/2609.07738/) (2026)
- [SiamMo: Siamese Motion-Centric 3D Object Tracking](https://mlsanity.com/paper/2408.01688/) (2024)
- [EasyTrack: Efficient and Compact One-stream 3D Point Clouds Tracker](https://mlsanity.com/paper/2404.05960/) (2024)
- [PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences](https://mlsanity.com/paper/2603.19762/) (2026)

## Abstract (arXiv)

3D LiDAR-based single object tracking (SOT) has gained increasing attention as it plays a crucial role in 3D applications such as autonomous driving. The central problem is how to learn a target-aware representation from the sparse and incomplete point clouds. In this paper, we propose a novel Correlation Pyramid Network (CorpNet) with a unified encoder and a motion-factorized decoder. Specifically, the encoder introduces multi-level self attentions and cross attentions in its main branch to enrich the template and search region features and realize their fusion and interaction, respectively. Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features. The output features of the search region from the encoder can be directly fed into the decoder for predicting target locations without any extra matcher. Moreover, in the decoder of CorpNet, we design a motion-factorized head to explicitly learn the different movement patterns of the up axis and the x-y plane together. Extensive experiments on two commonly-used datasets show our CorpNet achieves state-of-the-art results while running in real-time.