E-TraMamba: A New Paradigm for Efficient Long-Term 3D Feature Tracking with Event Cameras
2026-07-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionRobotics
AI summaryⓘ
The authors created E-TraMamba, a new method to track 3D features using event camera data, which is very fast and works well even with blurry or hidden objects. Their approach uses a smart model to understand long-term changes efficiently and combines different types of data into one smooth tracking system. They also made a big synthetic dataset called EvD-PointOdyssey for training and testing such trackers. Tests show that their method keeps tracking features longer and more accurately than other methods, making it useful for real-time robot navigation and mapping.
event-based tracking3D feature trackinglinear state-space modelaffine transformspatiotemporal dependenciesmulti-scale fusionevent camerasvisual odometrySLAMsynthetic dataset
Authors
Juwei Shen, Yujie Wu, Changwen Chen
Abstract
Event-based 3D tracking enables low-latency and high-speed perception, while existing CNN- and Transformer-based trackers struggle to capture long-range spatiotemporal dependencies in sparse, noisy event streams, especially under real-time and efficiency constraints. To address these challenges, we present E-TraMamba, the first Mamba-based framework for 3D feature tracking on event data. This new framework adopts a linear state-space model for efficient long-range modeling and integrates a lightweight affine-transform predictor to maintain stable tracking under motion blur and occlusion. We also design an effective scheme to fuse multi-scale cues -- local spatiotemporal patches, correlation maps, and positional embeddings -- into a unified representation that enables stable and smooth 3D tracking. We construct a large-scale synthetic dataset, named EvD-PointOdyssey, which is generated with monocular rendering and provides synchronized event streams, depth maps, and accurate 3D trajectories for training and evaluating event-based 3D tracking models. Extensive experiments on event-based benchmarks demonstrate that E-TraMamba achieves state-of-the-art performance, delivering over $2\times$ longer feature lifetimes under strict accuracy thresholds (e.g., 0.1 m), with higher tracked-feature ratios and lower RMSE than all baselines. These results make E-TraMamba a strong candidate for low-latency visual odometry, real-time SLAM, and interactive robotics.