arXiv · 2611.20737
CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking
Abstract
A social robot has to keep track of the people around it over time to plan its motion, a task handled by 3D multi-object tracking. For the LiDAR modality, trackers usually sit on top of a detector and link its detections across frames with a separate motion model or re-identification network. We instead show how a 3D LiDAR detector itself can be turned into a tracker by adding an instance-level contrastive objective on its intermediate voxel features. Each embedding is read from the voxels inside a detected box, and boxes are matched across frames by cosine similarity and the Hungarian algorithm, without a motion model. The detector backbone is fine-tuned together with this objective, which learns identity-aware features while leaving detection accuracy essen- tially intact. Because the method uses only the voxel features that Li- DAR detectors already produce, it is backbone-agnostic. On the JRDB 3D tracking leaderboard our LiDAR-only tracker ranks first on HOTA (38.58) and IDF1 (37.99), 13.04 and 9.30 points above the next pub- lished method, and second on MOTA and OSPA. Code is available at https://hermak56.github.io/CLIFT/.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
German Devchich, Timur Akhtyamov, Denis Fatykhoph, Gonzalo Ferrer. 2026-11-16. CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking. https://searcharxiv.com/abs/2611.20737
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.