Browse State-of-the-Art › 3D Multi-Object Tracking
3D Multi-Object Tracking
49 papers with code · 6 benchmarks · 6 datasets archive 2025-07-28
Image: Weng et al
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| nuScenes (115 rows) | MCTrack | MCTrack: A Unified 3D Multi-Object Tracking Framework for... | code | — | Compare |
| Waymo Open Dataset: Vehicle (Online Methods) (16 rows) | RobMOT | RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and... | code | — | Compare |
| nuscenes Camera-Radar (4 rows) | SpaRC | SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection | — | — | Compare |
| Waymo Open Dataset (3 rows) | DetZero | DetZero: Rethinking Offboard 3D Object Detection with Long-term... | code | Syntology ran 1 of 8 samples · 7 unverified | Compare |
| nuScenes Camera Only (1 row) | StreamPETR-Large | Exploring Object-Centric Temporal Modeling for Efficient... | code | — | Compare |
| nuScenes LiDAR only (1 row) | VoxelNeXt | VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking | code | Syntology ran 0 of 6 samples · 6 unverified | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
6 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Most implemented papers archive 2025-07-28
30 shown of 49 papers with code (101 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
21 Mar 2017 75 repositories listed Syntology ran 12 of 40 samples · 28 unverified · 7 pointer-only (licence)Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
-
19 Jun 2020 13 repositories listed Syntology ran 7 of 22 samples · 15 unverifiedThree-dimensional objects are commonly represented as 3D boxes in a point-cloud.
-
8 Mar 2022 6 repositories listedJoint detection and embedding (JDE) based methods usually estimate bounding boxes and embedding features of objects with a single network in Multi-Object Tracking (MOT).
-
28 May 2024 3 repositories listedSpecifically, we exploit the 2D detections and extracted features from multiple cameras to provide a better approximation of the multi-object filtering density to realize the track initiation/termination and…
-
23 Aug 2021 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)3D multi-object tracking in LiDAR point clouds is a key ingredient for self-driving vehicles.
-
29 Apr 2021 3 repositories listed Syntology ran 0 of 4 samples · 4 unverifiedMulti-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time.
-
16 Jan 2020 3 repositories listedOur method estimates the object states by adopting a Kalman Filter.
-
26 Sep 2023 2 repositories listedHowever, their proposed methods mainly use cooperative detection results as input to a standard single-sensor Kalman Filter-based tracking algorithm.
-
7 Aug 2023 2 repositories listedConsequently, we develop a suite of components to complement the virtual voxel concept, including a virtual voxel encoder, a virtual voxel mixer, and a virtual voxel assignment strategy.
-
21 Mar 2023 2 repositories listedOn the standard nuScenes benchmark, it is the first online multi-view method that achieves comparable performance (67.
-
29 Jun 2022 2 repositories listedOur novel sparse feature sampling module only utilizes local 2D region of interest (RoI) features calculated by the projection of 3D query boxes for further box refinement, leading to a fully-convolutional and…
-
26 May 2022 2 repositories listed Syntology ran 3 of 10 samples · 7 unverifiedMulti-sensor fusion is essential for an accurate and reliable autonomous driving system.
-
9 Feb 2022 2 repositories listedBy modeling the entire time-lapse sequence as a direct graph where cell instances are represented by its nodes and their associations by its edges, we extract the entire set of cell trajectories by looking for the…
-
18 Nov 2021 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified3D multi-object tracking (MOT) has witnessed numerous novel benchmarks and approaches in recent years, especially those under the "tracking-by-detection" paradigm.
-
25 Oct 2021 2 repositories listedFinally, we use a pre-rendered sparse viewpoint model to create a joint posterior probability for the object pose.
-
2 Jan 2025 1 repository listedThe evolution of Advanced Driver Assistance Systems (ADAS) has increased the need for robust and generalizable algorithms for multi-object tracking.
-
19 Oct 2024 1 repository listedHowever, both filters depend on overlapping fields of view from the cameras to combine complementary information.
-
2 Oct 2024 1 repository listedTo address this limitation, we introduce open-vocabulary 3D tracking, which extends the scope of 3D tracking to include objects beyond predefined categories.
-
23 Sep 2024 1 repository listedThis paper introduces MCTrack, a new 3D multi-object tracking method that achieves state-of-the-art (SOTA) performance across KITTI, nuScenes, and Waymo datasets.
-
18 Sep 2024 1 repository listed3D Multi-Object Tracking (MOT) obtains significant performance improvements with the rapid advancements in 3D object detection, particularly in cost-effective multi-camera setups.
-
31 Jul 2024 1 repository listedPerception systems of autonomous vehicles are susceptible to occlusion, especially when examined from a vehicle-centric perspective.
-
26 Jun 2024 1 repository listedCompared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full track optimization but has to deal with…
-
19 May 2024 1 repository listedRobMOT excels in challenging scenarios, tracking distant objects and prolonged occlusions, with a 1.
-
14 May 2024 1 repository listedTracking-by-attention, however, entangles detection and tracking queries in one embedding for both the detection and tracking task, which is sub-optimal.
-
22 Mar 2024 1 repository listedTo enable self-driving vehicles accurate detection and tracking of surrounding objects is essential.
-
20 Mar 2024 1 repository listed3D Multi-Object Tracking (MOT) captures stable and comprehensive motion states of surrounding obstacles, essential for robotic perception.
-
12 Mar 2024 1 repository listedHyDRa achieves a new state-of-the-art for camera-radar fusion of 64.
-
2 Oct 2023 1 repository listedIn this work, we propose an offline tracking model that focuses on occluded object tracks.
-
12 Sep 2023 1 repository listedThese provide the first benchmark and important insights for the future development of 4D imaging radar-based online 3D MOT algorithms.
-
22 Aug 2023 1 repository listedIn this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches.
Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections