3D Single Object Tracking

21 papers with code • 0 benchmarks • 1 datasets

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.


Use these libraries to find 3D Single Object Tracking models and implementations


Most implemented papers

Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds

ghostish/open3dsot ICCV 2021

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.

VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images

opendr-eu/opendr 6 Jun 2022

In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT).

GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds

haooozi/glt-t 20 Nov 2022

Technically, 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 points, thus providing more robust and accurate cues for offset learning.

Variational Voxel Pseudo Image Tracking

opendr/variational-voxel-3d-detetction 12 Feb 2023

Uncertainty 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 predictions to the decision method or a human supervisor.

OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking

haooozi/osp2b 23 Apr 2023

By integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals and further mitigate task misalignment.

M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object Tracking

ywu0912/teamcode 11 Dec 2023

3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving.

PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds

shanjiayao/ptt 14 Aug 2021

Our code is open-sourced for the robotics community at https://github. com/shanjiayao/PTT.

Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

ghostish/open3dsot CVPR 2022

3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving.

A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds

jimmy-dq/dmt 8 Mar 2022

Recent 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.

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

fpthink/stnet 25 Jul 2022

Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area.