Browse State-of-the-Art › 3D Single Object Tracking
3D Single Object Tracking
26 papers with code · 0 benchmarks · 1 dataset archive 2025-07-28
3D tracking of a single object, based on an initial 3D bounding box, provided to the tracker. 3D single object tracking is commonly performed using point cloud data from Lidars, as it provides valuable depth information, which is lost in camera images. However, irregular point cloud structure and an increasing point sparsity with distance makes Lidar-based 3D single object tracking a nontrivial task.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
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
1 dataset 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
26 shown of 26 papers with code (43 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.
-
11 Dec 2023 2 repositories listed3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving.
-
23 Apr 2023 2 repositories listedBy integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals and further mitigate task misalignment.
-
12 Feb 2023 2 repositories listedUncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its…
-
20 Nov 2022 2 repositories listedTechnically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed…
-
6 Jun 2022 2 repositories listedIn this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT).
-
10 Aug 2021 2 repositories listed Syntology ran 0 of 4 samples · 4 unverifiedCurrent 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.
-
3 Dec 2024 1 repository listedIn this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild.
-
3 Dec 2024 1 repository listed3D single object tracking is essential in autonomous driving and robotics.
-
3 Aug 2024 1 repository listedWe also introduce a Box-aware Feature Encoding module to encode object size priors into motion estimation.
-
7 Jul 2024 1 repository listedMoreover, under the same point-based representation, P2P-point outperforms the previous motion tracker M²Track by \textbf{3.
-
11 Apr 2024 1 repository listedLiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving.
-
26 Feb 2024 1 repository listedMost existing methods perform tracking between two consecutive frames while ignoring the motion patterns of the target over a series of frames, which would cause performance degradation in the scenes with sparse points.
-
18 Dec 2023 1 repository listedInstead of performing correlation of the two branches at just one point in the network, in this paper, we present a multi-correlation Siamese Transformer network that has multiple stages and carries out feature…
-
5 Sep 2023 1 repository listed3D Single Object Tracking (SOT) is a fundamental task of computer vision, proving essential for applications like autonomous driving.
-
23 Aug 2023 1 repository listed3D single object tracking with LiDAR points is an important task in the computer vision field.
-
11 May 2023 1 repository listedTo overcome the limitations of geometry matching, we propose a Multi-modal Multi-level Fusion Tracker (MMF-Track), which exploits the image texture and geometry characteristic of point clouds to track 3D target.
-
1 Apr 2023 1 repository listedIncorporating this transformer-based voting scheme into 3D RPN, a novel Siamese method dubbed GLT-T is developed for 3D single object tracking on point clouds.
-
21 Mar 2023 1 repository listedDue to the motion-centric nature, our method shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training.
-
16 Mar 2023 1 repository listed Syntology ran 0 of 1 samples · 1 unverifiedSpecifically, we introduce two cycle-consistency strategies for supervision: 1) Self tracking cycles, which leverage labels to help the model converge better in the early stages of training; 2) forward-backward cycles,…
-
14 Nov 2022 1 repository listedAccording to the experiment results, the class-specific object tracker performed better than the generic object tracker in terms of stability and accuracy.
-
2 Oct 2022 1 repository listedMeanwhile, the encoder applies the attention on multi-scale features to compensate for the lack of information caused by the sparsity of point cloud and the single scale of features.
-
2 Sep 2022 1 repository listedPTT module in the voting stage could model the interactions among point patches, which learns context-dependent features.
-
25 Jul 2022 1 repository listedSiamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area.
-
8 Mar 2022 1 repository listedRecent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking.
-
3 Mar 2022 1 repository listed3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving.
-
14 Aug 2021 1 repository listedOur code is open-sourced for the robotics community at https://github.
Syntology lines on 2 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