CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

• URL: http://arxiv.org/abs/2511.15580v3
• Date: Sat, 22 Nov 2025 13:51:00 GMT
• Title: CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking
• Abstract summary: 3D single object tracking in LiDAR point clouds is a critical task in computer vision and autonomous driving.<n>Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge.<n>We propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds.
• Score: 43.89894227481455
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU.

Related papers

• RRTrack: Robust and Recoverable Object 6D Pose Tracking for Dynamic Scenes [55.15267980622371]
  RRTrack is an efficient, recoverable object 6D pose tracker.<n>It enables robust tracking through fast motion and target disappearance--reappearance.<n>Experiments show RRTrack improves equal-subset mean ADD-S AR by 66.3% and ADD-S AUC by 65.7% over FoundationPose.
  arXiv  Detail & Related papers  (2026-07-26T14:05:46Z)
• Tri-Efficient Transfer Learning for Point Cloud Videos [32.14641034344552]
  PoinTriE aims to mine richer supervision signals from existing data rather than blindly scaling datasets.<n>For pre-training, pseudo-motion trajectories are synthesized via rigid transformations, paired with text corpora and 2D projections derived from raw point clouds.<n>During fine-tuning, we freeze the pretrained backbone and only update a lightweight Spatio-temporal Side Network built with LoRA units.
  arXiv  Detail & Related papers  (2026-06-23T05:55:02Z)
• Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking [13.622939944601393]
  TrajTrack is a lightweight framework that enhances a base two-frame tracker by implicitly learning motion continuity from historical bounding box trajectories alone.<n>It achieves new state-of-the-art performance, dramatically improving tracking precision by 4.48% over a strong baseline while running at 56 FPS.
  arXiv  Detail & Related papers  (2025-09-14T21:57:16Z)
• LiDAR MOT-DETR: A LiDAR-based Two-Stage Transformer for 3D Multiple Object Tracking [4.65812324892521]
  We present a lidar-based two-staged DETR inspired transformer; a smoother and tracker.<n>The smoother stage refines lidar object detections, from any off-the-shelf detector, across a moving temporal window.<n>The tracker stage uses a DETR-based attention block to maintain tracks across time by associating tracked objects with the refined detections using the point cloud as context.
  arXiv  Detail & Related papers  (2025-05-19T06:25:48Z)
• Online Dense Point Tracking with Streaming Memory [54.22820729477756]
  Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video.<n>Recent point tracking algorithms usually depend on sliding windows for indirect information propagation from the first frame to the current one.<n>We present a lightweight and fast model with textbfStreaming memory for dense textbfPOint textbfTracking and online video processing.
  arXiv  Detail & Related papers  (2025-03-09T06:16:49Z)
• Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking [54.124445709376154]
  We propose a novel asymmetric Siamese tracker named textbfAsymTrack for efficient tracking.<n>Building on this architecture, we devise an efficient template modulation mechanism to inject crucial cues into the search features.<n>Experiments demonstrate that AsymTrack offers superior speed-precision trade-offs across different platforms.
  arXiv  Detail & Related papers  (2025-03-01T14:44:54Z)
• VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking [3.517993407670811]
  Current LiDAR point cloud-based 3D single object tracking (SOT) methods typically rely on point-based representation network. We introduce a novel tracking framework, termed VoxelTrack. By voxelizing inherently disordered point clouds into 3D voxels, VoxelTrack effectively models precise and robust 3D spatial information.
  arXiv  Detail & Related papers  (2024-08-05T06:38:43Z)
• PointCompress3D: A Point Cloud Compression Framework for Roadside LiDARs in Intelligent Transportation Systems [24.783727646151583]
  This work introduces PointCompress3D, a novel point cloud compression framework tailored specifically for roadside LiDARs. We adapt, extend, integrate, and evaluate three cutting-edge compression methods using our real-world-based TUMTraf dataset family. In extensive experiments and ablation studies, we finally achieved a PSNR d2 of 94.46 and a BPP of 6.54 on our dataset.
  arXiv  Detail & Related papers  (2024-05-02T21:35:45Z)
• Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
  We propose DyTrack, a dynamic transformer framework for efficient tracking.<n>DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget.<n>Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
  arXiv  Detail & Related papers  (2024-03-26T12:31:58Z)
• Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking [2.487142846438629]
  3 single object tracking within LIDAR point is pivotal task in computer vision. Existing methods, which depend solely on appearance matching via networks or utilize information from successive frames, encounter significant challenges. We design an innovative cross-frame bi-temporal motion tracker, named STMD-Tracker, to mitigate these challenges.
  arXiv  Detail & Related papers  (2024-03-23T13:15:44Z)
• BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View [54.48052449493636]
  3D Single Object Tracking (SOT) is a fundamental task in computer vision and plays a critical role in applications like autonomous driving.<n>We propose BEVTrack, a simple yet effective motion-based tracking method.<n>We show that BEVTrack achieves state-of-the-art results while operating at 200 FPS, enabling real-time applicability.
  arXiv  Detail & Related papers  (2023-09-05T12:42:26Z)
• CXTrack: Improving 3D Point Cloud Tracking with Contextual Information [59.55870742072618]
  3D single object tracking plays an essential role in many applications, such as autonomous driving. We propose CXTrack, a novel transformer-based network for 3D object tracking. We show that CXTrack achieves state-of-the-art tracking performance while running at 29 FPS.
  arXiv  Detail & Related papers  (2022-11-12T11:29:01Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.