MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation

TL;DR

MambaTrack3D introduces a novel LiDAR object tracking framework optimized for high temporal variation environments, combining efficient inter-frame propagation and semantic feature enhancement to improve accuracy and computational efficiency.

Contribution

It presents a new state space model-based tracking framework with a Mamba-based inter-frame propagation module and grouped feature enhancement, addressing computational and redundancy issues in HTV scenarios.

Findings

Outperforms existing HTV trackers on KITTI-HTV and nuScenes-HTV benchmarks.

Achieves up to 6.5 success and 9.5 precision improvements over HVTrack.

Maintains competitive performance on standard KITTI dataset.

Abstract

Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers often suffer from quadratic computational complexity, temporal redundancy, and insufficient exploitation of geometric priors. To address these issues, we propose MambaTrack3D, a novel HTV-oriented tracking framework built upon the state space model Mamba. Specifically, we design a Mamba-based Inter-frame Propagation (MIP) module that replaces conventional single-frame feature extraction with efficient inter-frame propagation, achieving near-linear complexity while explicitly modeling spatial relations across historical frames. Furthermore, a Grouped Feature Enhancement Module (GFEM) is introduced to separate foreground and background semantics at the channel level, thereby mitigating temporal redundancy in the memory bank. Extensive experiments on KITTI-HTV and nuScenes-HTV benchmarks demonstrate that MambaTrack3D consistently outperforms both HTV-oriented and normal-scenario trackers, achieving improvements of up to 6.5 success and 9.5 precision over HVTrack under moderate temporal gaps. On the standard KITTI dataset, MambaTrack3D remains highly competitive with state-of-the-art normal-scenario trackers, confirming its strong generalization ability. Overall, MambaTrack3D achieves a superior accuracy-efficiency trade-off, delivering robust performance across both specialized HTV and conventional tracking scenarios.