Pose Tracking

60 papers with code • 3 benchmarks • 9 datasets

Pose Tracking is the task of estimating multi-person human poses in videos and assigning unique instance IDs for each keypoint across frames. Accurate estimation of human keypoint-trajectories is useful for human action recognition, human interaction understanding, motion capture and animation.

Source: LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

Libraries

Use these libraries to find Pose Tracking models and implementations
3 papers
4,877
2 papers
2,911
See all 6 libraries.

VideoMAC: Video Masked Autoencoders Meet ConvNets

nust-machine-intelligence-laboratory/videomac 29 Feb 2024

In this paper, we propose a new approach termed as \textbf{VideoMAC}, which combines video masked autoencoders with resource-friendly ConvNets.

8
29 Feb 2024

Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker

s-jingtao/ick-track 9 Jan 2024

In this paper, we investigate the real-world robot task of aerial vision guidance for aerial robotics manipulation, utilizing category-level 6-DoF pose tracking.

24
09 Jan 2024

PACE: Pose Annotations in Cluttered Environments

qq456cvb/pace 23 Dec 2023

Addressing this, we introduce PACE (Pose Annotations in Cluttered Environments), a large-scale benchmark designed to advance the development and evaluation of pose estimation methods in cluttered scenarios.

8
23 Dec 2023

EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping

arclab-hku/event_based_vo-vio-slam 19 Dec 2023

To the best of our knowledge, this is the first non-learning work to realize event-based dense mapping.

180
19 Dec 2023

Deep Event Visual Odometry

tum-vision/devo 15 Dec 2023

To remove the dependency on additional sensors and to push the limits of using only a single event camera, we present Deep Event VO (DEVO), the first monocular event-only system with strong performance on a large number of real-world benchmarks.

34
15 Dec 2023

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

NVlabs/FoundationPose 13 Dec 2023

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups.

385
13 Dec 2023

Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia

taatiteam/pose2gait_public 22 Aug 2023

In this work we train a deep neural network to map from a two dimensional pose sequence, extracted from a video of an individual walking down a hallway toward a wall-mounted camera, to a set of three-dimensional spatiotemporal gait features averaged over the walking sequence.

2
22 Aug 2023

Humans in 4D: Reconstructing and Tracking Humans with Transformers

shubham-goel/4D-Humans ICCV 2023

To analyze video, we use 3D reconstructions from HMR 2. 0 as input to a tracking system that operates in 3D.

975
31 May 2023

Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)

twyncoder/vidimu-tools 27 Mar 2023

Human activity recognition and clinical biomechanics are challenging problems in physical telerehabilitation medicine.

5
27 Mar 2023

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

NVlabs/BundleSDF CVPR 2023

We present a near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence, while simultaneously performing neural 3D reconstruction of the object.

849
24 Mar 2023