Offline-Poly: A Polyhedral Framework For Offline 3D Multi-Object Tracking

• URL: http://arxiv.org/abs/2602.13772v1
• Date: Sat, 14 Feb 2026 13:34:21 GMT
• Title: Offline-Poly: A Polyhedral Framework For Offline 3D Multi-Object Tracking
• Authors: Xiaoyu Li, Yitao Wu, Xian Wu, Haolin Zhuo, Lijun Zhao, Lining Sun,
• Abstract summary: offline 3D MOT is a critical component of the 4D auto-labeling process.<n>We propose Offline-Poly, a general offline 3D MOT method based on a tracking-centric design.
• Score: 11.527022085205012
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Offline 3D multi-object tracking (MOT) is a critical component of the 4D auto-labeling (4DAL) process. It enhances pseudo-labels generated by high-performance detectors through the incorporation of temporal context. However, existing offline 3D MOT approaches are direct extensions of online frameworks and fail to fully exploit the advantages of offline setting. Moreover, these methods often depend on fixed upstream and customized architectures, limiting their adaptability. To address these limitations, we propose Offline-Poly, a general offline 3D MOT method based on a tracking-centric design. We introduce a standardized paradigm termed Tracking-by-Tracking (TBT), which operates exclusively on arbitrary off-the-shelf tracking outputs and produces offline-refined tracklets. This formulation decouples offline tracker from specific upstream detectors or trackers. Under the TBT paradigm, Offline-Poly accepts one or multiple coarse tracking results and processes them through a structured pipeline comprising pre-processing, hierarchical matching and fusion, and tracklet refinement. Each module is designed to capitalize on the two fundamental properties of offline tracking: resource unconstrainedness, which permits global optimization beyond real-time limits, and future observability, which enables tracklet reasoning over the full temporal horizon. Offline-Poly first eliminates short-term ghost tracklets and re-identifies fragmented segments using global scene context. It then constructs scene-level similarity to associate tracklets across multiple input sources. Finally, Offline-Poly refines tracklets by jointly leveraging local and global motion patterns. On nuScenes, we achieve SOTA performance with 77.6% AMOTA. On KITTI, it achieves leading results with 83.00% HOTA. Comprehensive experiments further validate the flexibility, generalizability, and modular effectiveness of Offline-Poly.

Related papers

• FutrTrack: A Camera-LiDAR Fusion Transformer for 3D Multiple Object Tracking [4.65812324892521]
  FutrTrack builds on existing 3D detectors by introducing a transformer-based smoother and a fusion-driven tracker.<n>Our fusion tracker integrates bounding boxes with multimodal bird's-eye-view (BEV) fusion features from multiple cameras and LiDAR.<n>FutrTrack achieves strong performance on 3D MOT benchmarks, reducing identity switches while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-22T19:25:01Z)
• NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking [31.46043749958963]
  NOOUGAT is the first tracker to operate with arbitrary temporal horizons.<n>It improves textitonline AssA by +2.3 on DanceTrack, +9.2 on SportsMOT, and +5.0 on MOT20, with even greater gains in textitoffline mode.
  arXiv  Detail & Related papers  (2025-09-02T09:08:24Z)
• 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)
• CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking [68.24998698508344]
  We introduce CAMEL, a novel association module for Context-Aware Multi-Cue ExpLoitation.<n>Unlike end-to-end detection-by-tracking approaches, our method remains lightweight and fast to train while being able to leverage external off-the-shelf models.<n>Our proposed online tracking pipeline, CAMELTrack, achieves state-of-the-art performance on multiple tracking benchmarks.
  arXiv  Detail & Related papers  (2025-05-02T13:26:23Z)
• Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking? [36.5272157173876]
  Multi-Object Tracking (MOT) has demonstrated success in short-term association within the separated tracking-by-detection online paradigm.<n>In this paper, we review the concept of trajectory graphs and propose a novel perspective by representing them as directed acyclic graphs.<n>We introduce a concise Pure Transformer (PuTR) to validate the effectiveness of Transformer in unifying short- and long-term tracking for separated online MOT.
  arXiv  Detail & Related papers  (2024-05-23T02:44:46Z)
• An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds [50.19288542498838]
  3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. We introduce a motion-centric paradigm to handle LiDAR SOT from a new perspective.
  arXiv  Detail & Related papers  (2023-03-21T17:28:44Z)
• Modeling Continuous Motion for 3D Point Cloud Object Tracking [54.48716096286417]
  This paper presents a novel approach that views each tracklet as a continuous stream. At each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank. To enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed.
  arXiv  Detail & Related papers  (2023-03-14T02:58:27Z)
• 3DMODT: Attention-Guided Affinities for Joint Detection & Tracking in 3D Point Clouds [95.54285993019843]
  We propose a method for joint detection and tracking of multiple objects in 3D point clouds. Our model exploits temporal information employing multiple frames to detect objects and track them in a single network.
  arXiv  Detail & Related papers  (2022-11-01T20:59:38Z)
• Learnable Online Graph Representations for 3D Multi-Object Tracking [156.58876381318402]
  We propose a unified and learning based approach to the 3D MOT problem. We employ a Neural Message Passing network for data association that is fully trainable. We show the merit of the proposed approach on the publicly available nuScenes dataset by achieving state-of-the-art performance of 65.6% AMOTA and 58% fewer ID-switches.
  arXiv  Detail & Related papers  (2021-04-23T17:59:28Z)
• Segment as Points for Efficient Online Multi-Object Tracking and Segmentation [66.03023110058464]
  We propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. Our method generates a new tracking-by-points paradigm where discriminative instance embeddings are learned from randomly selected points rather than images. The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods by large margins.
  arXiv  Detail & Related papers  (2020-07-03T08:29:35Z)

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.