stargan-v2
VIBE
| stargan-v2 | VIBE | |
|---|---|---|
| 1 | 5 | |
| 3,418 | 2,802 | |
| 0.2% | - | |
| 0.0 | 0.0 | |
| about 1 year ago | about 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
stargan-v2
-
How to Run stargan2 on Google Colab
This version of StarGAN2 (coined as 'Post-modern Style Transfer') is intended mostly for fellow artists, who rarely look at scientific metrics, but rather need a working creative tool. At least, this is what I use nearly daily myself. Here are few pieces, made with it: Terminal Blink, Occurro, etc. Tested on Pytorch 1.4-1.8. Sequence-to-video conversions require FFMPEG. For more explicit details refer to the original implementation.
VIBE
- 3D reconstruction models for human body
-
Any ghetto Mo'Cap solutions?
there are projects like this and similar, that are able to create motion capture from video: https://github.com/KevinLTT/video2bvh or https://github.com/mkocabas/VIBE
- My experience using VIBE ( free motion extraction tool for animation )
- Free deep learning tool for extracting animation from videos (link in post)
-
Markerless Motion Capture - Turning Videos into 3D Animations
Another Edit: Here's another one that supports FBX export out of the box: https://github.com/mkocabas/VIBE
What are some alternatives?
AvatarMe - Public repository for the CVPR 2020 paper AvatarMe and the TPAMI 2021 AvatarMe++
video2bvh - Extracts human motion in video and save it as bvh mocap file.
ALAE - [CVPR2020] Adversarial Latent Autoencoders
frankmocap - A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
stargan2 - StarGAN2 for practice
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
meshed-memory-transformer - Meshed-Memory Transformer for Image Captioning. CVPR 2020
mediapipe - Cross-platform, customizable ML solutions for live and streaming media.
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
smplx - SMPL-X
SMPL - NumPy, TensorFlow and PyTorch implementation of human body SMPL model and infant body SMIL model.
kapao - KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.