[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Grounding Image Matching in 3D with MASt3R

A retro game engine for Python

VPoser: Variational Human Pose Prior

Official Repository for FreeMan dataset

This repository provides motion datasets collected by Bandai Namco Research Inc

API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset

Official implementation of Transformer-Based Multi-Grained Features for Person Re-Identification (WACV23 workshop).

Official codebase for 3D-LFM paper. Accepted at CVPR, 2024.

A large-scale video dataset for the training and evaluation of 3D human pose estimation models

OpenMMLab Pose Estimation Toolbox and Benchmark.

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"

Code for "HumVis: Human-Centric Visual Analysis System", ACM MM 2023 Demo

Video anonymization by face detection

Download a copy of your Garmin Connect data, including stats and GPX tracks.

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

YACS -- Yet Another Configuration System

This repo is official implementation of HumanBench (CVPR2023)

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[CVPR 2022] Part-based Pseudo Label Refinement for Unsupervised Person Re-identification

A python package for turning sports video into csv files

Main OpenCap processing pipeline

Utilities for processing OpenCap data.