Thomas Goussaert's starred repositories

Language:C++Stargazers:6Issues:0Issues:0
Language:C#License:MITStargazers:81Issues:0Issues:0

ObjectBrowser

Allows browsing all live UObjects in real-time.

Language:C++License:MITStargazers:78Issues:0Issues:0

awesome-secure-saas-apis

A catalog of SaaS APIs and their security levels, compliance, and regulation like GDPR, ISO27001, PCI and others

Stargazers:122Issues:0Issues:0

tracy

Frame profiler

Language:C++License:NOASSERTIONStargazers:9847Issues:0Issues:0

tutorials

Tutorials for creating and using ONNX models

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:3348Issues:0Issues:0

netron

Visualizer for neural network, deep learning and machine learning models

Language:JavaScriptLicense:MITStargazers:27728Issues:0Issues:0

vive_ik_demo

A full body tracking demo using HTC Vive and Trackers

Language:C#Stargazers:311Issues:0Issues:0

few-shot-vid2vid

Pytorch implementation for few-shot photorealistic video-to-video translation.

Language:PythonLicense:NOASSERTIONStargazers:1799Issues:0Issues:0

MocapNET

We present MocapNET, 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 monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance

Language:C++License:NOASSERTIONStargazers:845Issues:0Issues:0

EvoSkeleton

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"

Language:PythonLicense:MITStargazers:333Issues:0Issues:0

Unity-VRIK-Calibration

Calibration Script for VRIK and SteamVR in Unity

Language:C#License:MITStargazers:4Issues:0Issues:0

VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

Language:PythonLicense:NOASSERTIONStargazers:2879Issues:0Issues:0

npybvh

Biovision Hierarchy (BVH) reader for python with numpy pose output

Language:PythonLicense:MITStargazers:53Issues:0Issues:0

AI4Animation

Bringing Characters to Life with Computer Brains in Unity

Language:C++Stargazers:7820Issues:0Issues:0

DeepIK

Neural Networks for Inverse Kinematics

Language:PythonStargazers:68Issues:0Issues:0

RotationContinuity

Coder for "On the Continuity of Rotation Representations"

Language:PythonLicense:MITStargazers:331Issues:0Issues:0
Language:Jupyter NotebookStargazers:29Issues:0Issues:0

6d_rot_tensorflow

6D rotation representation ("On the Continuity of Rotation Representations in Neural Networks") for tensorflow

Language:PythonStargazers:18Issues:0Issues:0

LSTM_Pose_Machines

Code repo for "LSTM Pose Machines" (CVPR'18)

Language:Jupyter NotebookStargazers:276Issues:0Issues:0

3d-pose-baseline

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

Language:PythonLicense:MITStargazers:1413Issues:0Issues:0

3Dpose_ssl

3D Human Pose Machines with Self-supervised Learning

Language:C++Stargazers:412Issues:0Issues:0

ThreeDPoseUnitySample

Unity sample of 3D pose estimation

Language:C#Stargazers:363Issues:0Issues:0
Language:MathematicaLicense:Apache-2.0Stargazers:7Issues:0Issues:0

margipose

3D monocular human pose estimation

Language:PythonLicense:Apache-2.0Stargazers:98Issues:0Issues:0

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

Language:C++License:Apache-2.0Stargazers:26926Issues:0Issues:0

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Language:PythonLicense:Apache-2.0Stargazers:30110Issues:0Issues:0

Aim-IK

A Unity package, to procedurally orientate the character's head (and spine) in a direction without using any animation data.

Language:C#License:MITStargazers:331Issues:0Issues:0

UnityGenericIKSystem

An easy to understand, open source implementation of Inverse Kinematics for Unity 3D

Language:C#License:MITStargazers:172Issues:0Issues:0

MobileUNET

U-NET Semantic Segmentation model for Mobile

Language:Jupyter NotebookLicense:MITStargazers:50Issues:0Issues:0