Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.
Inference and fine-tuning examples for vision models from 🤗 Transformers
An unofficial implementation of ViTPose [Y. Xu et al., 2022]
Real-time pose estimation pipeline with 🤗 Transformers
VitPose without MMCV dependencies
TopDown Pose Estimation on iOS and PureSwift.
Repository to evaluate Deep Learning Models for funscript generation
Simple pipeline using Yolov5 and ViTPose to annotate human pose in videos.
TopDown Pose Estimation on iOS
Smooth and stabilise OpenPose in ComfyUI: removes pose jitter, hand flicker and dropped keypoints before ControlNet
14-keypoint car pose estimation on CarFusion — YOLO26-pose main + ViTPose-S baseline, FastAPI serving, HF Hub model
An annotation tool that combines TCFormer and ViTPose as an ensemble setup for COCO Wholebody annotations.
Multi-modal hand tracking fusion system: HaMeR + ViTPose + IMU glove + depth camera, with per-finger confidence-gated switching and Slerp complementary filter. Consolidated from 6 repos with full fusion algorithm docs, evaluation report, MIT License, and CITATION.cff.
Native MLX Swift ViTPose: on-device human pose estimation on Apple Silicon (HF-verified). No PyTorch, no cloud.
A novel approach to detecting violence in videos by using hierarchical attention networks.
Controlled benchmark of Vision Transformers for cervical-vertebra landmark localisation in videofluoroscopy. 169 archived runs collapsed into a 9-model x 6-configuration grid, 95% CI on every number, each re-derivable from a single run hash. 243 tests; no GPU or dataset needed to verify.
To associate your repository with the vitpose topic, visit your repo's landing page and select "manage topics."