[BMVC2023] Widely Applicable Strong Baseline for Sports Ball Detection and Tracking

DUSt3R: Geometric 3D Vision Made Easy

Code for "Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views" (CVPR 2019, T-PAMI 2021)

一本系统地教你将深度学习模型的性能最大化的战术手册。

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"

The official repository of the RePoGen paper

High-resolution models for human tasks.

Easy to use SOTA Top-Down Multi-person Pose Estimation Models in PyTorch

Official implementation for SIGGRAPH 2023 paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

A tool to fit SMPL parameters from 3D-pose datasets that contain key-points of human body.

Fisheye or Normal Camera Intrinsic and Extrinsic Calibration. Surround Camera Bird Eye View Generator.

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Bilibili Downloader. 一款命令行式哔哩哔哩下载器.

Blender 3.6, 3.3, 2.93 & 2.8x add-on that allows streaming of data into Blender without freezing the interface (using ZeroMQ sockets).

Blender Socket implementation with Matlab/Simulink for data visualization purposes

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Unofficial PyTorch implementation of TrackNet

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Ultralytics YOLO11 🚀

Development Kit for the SoccerNet Challenge