[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"
[ECCV-20] Official PyTorch implementation of HoughNet, a voting-based object detector.
Bottom-up whole-body pose estimation method in constant time.
OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos. (SMC 2022)
[AAAI 2024] UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning
PoseAnnotator is a simple Python tool with a GUI for annotating 2D human poses from images. It allows users to easily label key points on human figures for pose estimation tasks.
A simple project using MediaPipe and OpenCV to detect human body landmarks from video. Includes both 2D pose overlay on video and real-time 3D skeleton visualization with Matplotlib.
WholeBodyPose: an end-to-end framework for sign-language recognition from whole-body pose estimation (ICMV 2025).
CS-GY 6643 I Computer Vision (Fall 2024) - Final Project
To associate your repository with the 2d-pose-estimation topic, visit your repo's landing page and select "manage topics."