cs.CVNov 16, 2026

CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking

Authors: German Devchich, Timur Akhtyamov, Denis Fatykhoph, Gonzalo Ferrer

Organizations: Applied AI Institute, Moscow, Russia

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/.

Figures & tables

Explore similar work

CardsList
  1. Does Appearance Help? A Systematic Study of Image-Based Re-Identification in Online 3D Multi-Pedestrian Tracking

    Jun 5, 2026Eduardo Borges, Luís Garrote, Urbano J. NunesCamera-LiDAR Fusion3D MOT

  2. Fusion-Poly: A Polyhedral Framework Based on Spatial-Temporal Fusion for 3D Multi-Object Tracking

    Mar 9, 2026Xian Wu, Yitao Wu, Xiaoyu Li +3Asynchronous Multimodal Sensor Fusion3D MOT