# RegTrack: Simplicity Beneath Complexity in Robust Multi-Modal 3D Multi-Object Tracking

arXiv: https://arxiv.org/abs/2409.00618 · HTML: https://mlsanity.com/paper/2409.00618/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 56 of its 84 references that are in the map.
- First posted on arXiv 1 Sep 2024.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (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)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection](https://mlsanity.com/paper/2007.08856/) (2020)
- [CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training](https://mlsanity.com/paper/2210.01055/) (2022)
- [SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking](https://mlsanity.com/paper/2111.09621/) (2021)
- [EagerMOT: 3D Multi-Object Tracking via Sensor Fusion](https://mlsanity.com/paper/2104.14682/) (2021)
- [Monocular Quasi-Dense 3D Object Tracking](https://mlsanity.com/paper/2103.07351/) (2021)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs](https://mlsanity.com/paper/2206.10555/) (2022)
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking](https://mlsanity.com/paper/2303.10404/) (2023)

## Abstract (arXiv)

Existing 3D multi-object tracking (MOT) methods often sacrifice efficiency and generalizability for robustness, largely relying on complex association metrics derived from multi-modal architectures and class-specific motion priors. Challenging the rooted belief that greater complexity necessarily yields greater robustness, we propose a robust, efficient, and generalizable method for multi-modal 3D MOT, dubbed RegTrack. Inspired by Yang-Mills gauge theory, RegTrack is built upon a unified tri-cue encoder (UTEnc), comprising three tightly coupled components: a local-global point cloud encoder (LG-PEnc), a mixture-of-experts-based geometry encoder (MoE-GEnc), and an image encoder from a well-pretrained visual-language model. LG-PEnc efficiently encodes the spatial and structural information of point clouds to produce foundational representations for each object, whose pairwise similarities serve as the sole association metric. MoE-GEnc seamlessly interacts with LG-PEnc to model inter-object geometric relationships across frames, adaptively compensating for inter-frame object motion without relying on any class-specific priors. The image encoder is kept frozen and is used exclusively during training to provide a well-pretrained representation space. Point cloud representations are aligned to this space to supervise the motion compensation process, encouraging representation invariance across frames for the same object while enhancing discriminability among different objects. Through this formulation, RegTrack attains robust, efficient, and generalizable inference using only point cloud inputs, requiring just 2.6M parameters. Extensive experiments on KITTI and nuScenes show that RegTrack outperforms its thirty-five competitors.