rfilkov

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

yolov10

YOLOv10: Real-Time End-to-End Object Detection

yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

AlphaPose

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

AI4Animation

Bringing Characters to Life with Computer Brains in Unity

Depth-Anything

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

ByteTrack

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

mathnet-numerics

Math.NET Numerics

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Marigold

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

MotionBERT

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

PatchFusion

[CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

flowmap

Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

UniDepth

Universal Monocular Metric Depth Estimation

YOLO

An MIT rewrite of YOLOv9

ScoreHMR

ScoreHMR: Score-Guided Diffusion for 3D Human Recovery (CVPR 2024)

Depth-Anything-ONNX

ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

lap

Linear Assignment Problem solver (LAPJV/LAPMOD).

HolisticMotionCapture

HolisticMotionCapture is an application and package that can capture the motion of a person with only a monocular color camera and move the VRM avatar's pose, face, and hands.

HolisticBarracuda

HolisticBarracuda is the Unity Package that simultaneously estimates 33 pose, 21 per-hand, and 468 facial landmarks on the Unity Barracuda with GPU.

YOLOv8-pose

YOLOv8-pose implementation using PyTorch

OrbbecSDK_ROS2

OrbbecSDK ROS2 wrapper

com.doji.diffusers

A Unity package to run pretrained diffusion models like Stable Diffusion with Unity Sentis

yolo_pose

HoloLabDnnPackages

The HoloLab DNN Packages providing image recognition library using deep learning running on the Unity. This packages is implemented based on Unity Sentis.

movenet-3d-unity

MoveNet 3D pose detection sample in Unity Engine.

unity-barracuda-inference-yolox

This Unity package extends the functionality of the barracuda-inference-base package to perform object detection using YOLOX models.

OrbbecFirmware

This repository is used to store download links for firmware.

unity-barracuda-inference-base

This Unity package provides a foundation for performing inference with the Barracuda inference library. It includes a flexible base class to extend with task-specific packages.