Scientific Software
Updated 6 months ago

Pose2Sim — Peer-reviewed • Rank 16.1 • Science 100%

Pose2Sim: An open-source Python package for multiview markerless kinematics - Published in JOSS (2022)

Scientific Software
Updated 6 months ago

Sports2D — Peer-reviewed • Rank 13.4 • Science 100%

Sports2D: Compute 2D human pose and angles from a video or a webcam - Published in JOSS (2024)

Updated 6 months ago

deeplabcut-live • Rank 13.9 • Science 77%

SDK for running DeepLabCut on a live video stream

Updated 6 months ago

df3d • Rank 12.9 • Science 57%

Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.

Updated 6 months ago

openpifpaf • Rank 17.7 • Science 51%

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

Updated 6 months ago

vitpose • Rank 8.5 • Science 54%

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

Updated 5 months ago

aptv2 • Rank 3.3 • Science 54%

The official repo for the extension of [NeurIPS'22] "APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking": https://github.com/pandorgan/APT-36K

Updated 6 months ago

skellytracker • Rank 10.9 • Science 44%

A pose estimation and object detection/tracking backend for freemocap.

Updated 6 months ago

mocapnet • Rank 7.9 • Science 31%

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

Updated 5 months ago

https://github.com/aim-uofa/frozenrecon • Rank 6.0 • Science 23%

[ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models

Updated 6 months ago

ossid_code • Science 67%

Source code for OSSID: Online Self-Supervised Instance Detection by (And For) Pose Estimation

Updated 6 months ago

detrex • Science 62%

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

Updated 5 months ago

https://github.com/capjamesg/ts-pose-game • Science 13%

Compare your pose to Taylor Swift's poses during performances.

Updated 5 months ago

exococotools • Science 44%

Extended-OKS (Ex-OKS) package for human pose evaluation

Updated 6 months ago

replicant • Science 49%

replicAnt - generating annotated images of animals in complex environments with Unreal Engine

Updated 6 months ago

neural-mesh-model • Science 67%

Neural mesh models for 3D reasoning.

Updated 5 months ago

https://github.com/chenhongyiyang/egoposeformer • Science 13%

[ECCV 2024] EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation

Updated 6 months ago

posebh • Science 54%

PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation

Updated 6 months ago

probpose_code • Science 54%

The official repository for CVPR 2025 paper 'ProbPose: A Probabilistic Approach to 2D Human Pose Estimation'

Updated 6 months ago

roft • Science 67%

Real-time Optical Flow-aided 6D Object Pose and Velocity Tracking

Updated 5 months ago

bboxmaskpose • Science 54%

[ICCV 25] The official repository of paper 'Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle'