2655251820

2655251820's Stars

• UPBGE/uplogic

  This package contains the code necessary to run logic nodes alongside a wide array of utility functions and classes.

  Language:Python115

• godotengine/godot

  Godot Engine – Multi-platform 2D and 3D game engine

  Language:C++91.6k21.3k

• arcsikex/cascadeur_bridge

  This Blender addon is aimed to help you integrate Cascadeur into your workflow.

  Language:Python31614

• aresdevo/animaide

  AnimAide is a free add-on for Blender that has some helpful tools for animation.

  Language:Python72565

• carson-katri/dream-textures

  Stable Diffusion built-in to Blender

  Language:Python7.9k428

• vijishmadhavan/ArtLine

  A Deep Learning based project for creating line art portraits.

  Language:Jupyter Notebook3.6k374

• Sxela/ArcaneGAN

  ArcaneGAN

  65680

• easydiffusion/easydiffusion

  Easiest 1-click way to create beautiful artwork on your PC using AI, with no tech knowledge. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image.

  Language:JavaScript9.7k799

• qweryty/blender_cloth_physical_properties_compensation

  Language:Python8

• leverxgroup/esrgan

  Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution

  Language:Python15019

• chaiNNer-org/chaiNNer

  A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.

  Language:Python4.7k286

• justdark/UE_Android_LiveLink

  an android alternative implementation for unreal face live link

  Language:C++32097

• facemoji/mocap4face

  Cross-platform SDK for facial motion capture producing blendshapes and rigid head poses in 3D space in realtime from photos or videos.

  613113

• zju3dv/EasyMocap

  Make human motion capture easier.

  Language:Python3.7k458

• xianfei/SysMocap

  A real-time motion capture system for 3D virtual character animating.

  Language:JavaScript2.6k421

• yuyuyzl/EasyVtuber

  tha3, but run 40fps on 3080 with virtural webcam support

  Language:Python1.9k201

• yul85/movingcam

  Language:Python23437

• 4ian/GDevelop

  🎮 Open-source, cross-platform 2D/3D/multiplayer game engine designed for everyone.

  Language:JavaScript11.7k886

• 2655251820/close2mocap

  blender head mocap

  1

• cgtinker/BlendArMocap

  realtime motion tracking in blender using mediapipe and rigify

  Language:Python931114

• UPBGE/blender-addons

  Fork of blender-addons to include customized UPBGE addons

  Language:Python2112

• DanielSantosBA/Blender-Game-Engine

  41

• eliemichel/OpenMfxForBlender

  A branch of Blender featuring an OpenMfx modifier

  Language:C17819

• IzaZed/bricky-nodes

  Node wrappers for UPBGE's logic bricks to make them easier to organize

  Language:Python4

• xyzRIick/UPBGE-multiplayer-online

  UPBGEMultiplayerOnline is a base for creating online multiplayer games using 100% custom-made code. It's a free and open-source project with Python, designed and tested on UPBGE 0.2.4x (Blender Game Engine - BGE).

  Language:Python103

• CMU-Perceptual-Computing-Lab/openpose

  OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

  Language:C++31.4k7.9k

• nicknochnack/MediaPipeHandPose

  Language:Jupyter Notebook4336

• FORTH-ModelBasedTracker/mocapnet_rosnode

  A ROS node for the MocapNET 3D Pose Estimator

  Language:C++54

• FORTH-ModelBasedTracker/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++862137

• rwsarmstrong/strongtrack

  A python tool with facial landmark annotation and coefficient finder

  Language:Python31058