AI Agent Skills

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

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

A PyTorch re-implementation of CPN (Cascaded Pyramid Network for Multi-Person Pose Estimation)

Deep learned, NVIDIA-accelerated 3D object pose estimation

Keras version of Realtime Multi-Person Pose Estimation project

Multi-person Human Pose Estimation with HRNet in Pytorch

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model…

[ICCV 2019] Monocular depth estimation from a single image

Library for Fast and Flexible Human Pose Estimation

Universal Monocular Metric Depth Estimation

[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

Fall Detection using OpenPifPaf's Human Pose Estimation model

Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch