peterljq / OpenMMD
OpenMMD is an OpenPose-based application that can convert real-person videos to the motion files (.vmd) which directly implement the 3D model (e.g. Miku, Anmicius) animated movies.
☆899Updated 4 years ago
Alternatives and similar repositories for OpenMMD:
Users that are interested in OpenMMD are comparing it to the libraries listed below
- ☆977Updated 3 years ago
- A 3D virtual head control system for VTuber in Unity with smooth motion and robust facial expressions☆443Updated 3 years ago
- We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given…☆864Updated 2 months ago
- Convert video to the bvh motion file☆387Updated last year
- An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]☆1,590Updated 5 months ago
- Openposeの2D人間骨格データから3D関節データを生成し、その関節データを出力します。☆97Updated 4 years ago
- A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.☆302Updated 4 years ago
- Extracts human motion in video and save it as bvh mocap file.☆584Updated 4 years ago
- A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]☆564Updated 2 years ago
- Convert video to 3D pose in one-key.☆646Updated last year
- 3d-pose-baseline-vmd で出力した関節データをもとに、vmd(MMDモーションデータ)ファイルを生成します。☆55Updated 4 years ago
- Unity sample of 3D pose estimation☆362Updated 3 years ago
- Convert human motion from video to .bvh☆378Updated 5 years ago
- An Implementation of VTuber (Both 3D and Live2D) using Python and Unity. Providing face movement tracking, eye blinking detection, iris d…☆503Updated 2 years ago
- Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021☆1,263Updated 10 months ago
- Real-time 3D human pose estimation, implemented by tensorflow☆247Updated 4 months ago
- Training repository for OpenPose☆584Updated 3 years ago
- Project for paper "Learning 3D Human Dynamics from Video"☆630Updated 2 years ago
- A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.☆1,427Updated 4 years ago
- MikuMikuRig是一款集生成控制器,自动导入动画,自动布料为一体的blender插件☆547Updated last year
- 3D Human Pose Machines with Self-supervised Learning☆414Updated 4 years ago
- A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.☆984Updated 2 years ago
- Project page for End-to-end Recovery of Human Shape and Pose☆1,559Updated last year
- mmd_tools is a blender addon for importing Models and Motions of MikuMikuDance.☆1,065Updated 2 years ago
- 虚拟爱抖露(アイドル)共享计划, 是基于单目RGB摄像头的人眼与人脸特征点检测算法, 在实时3D面部捕捉以及模型驱动领域的应用.☆901Updated 6 months ago
- Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"☆828Updated last year
- Expressive Body Capture: 3D Hands, Face, and Body from a Single Image☆1,789Updated 9 months ago
- Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"☆662Updated last year
- ☆474Updated 5 years ago
- realtime 3D pose estimation for wild videos, embed 2d keypoints detector like hrnet alphapose and openpose☆262Updated 4 months ago