AI Agent Skills

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

[IROS 2021] BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

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…

Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"

:basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.

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 m…

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

Compute 2D human pose and angles from a video or a webcam.

Multi-person Human Pose Estimation with HRNet in Pytorch

Fall Detection using OpenPifPaf's Human Pose Estimation model

[CVPR 2024 - Oral] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences

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

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

:wave: :ok_hand: research codebase for depth-based hand pose estimation using dynamics based tracking and CNNs

To support and further the research in the field of portrait animation , we are excited to launch PhotoPoster, an open project for pose-driven image generation.