Official code and dataset release for "JAFPro: Joint Appearance Fusion and Propagation for Human Video Motion Transfer from Multiple Reference Images"
-
Updated
Jul 5, 2021 - Python
Official code and dataset release for "JAFPro: Joint Appearance Fusion and Propagation for Human Video Motion Transfer from Multiple Reference Images"
This repository contains the source code for the paper First Order Motion Model for Image Animation
Browser extension for DanceGenerator.AI - Turn any TikTok dance video into AI-generated dance. Make anyone dance with AI: people, pets, cats, dogs, anime characters. One-click motion transfer from TikTok to AI dance video.
A Keras-based motion transfer model leveraging first-order Jacobian-based motion estimation to animate a static image using keypoints, inspired by Aliaksandr Siarohin's first-order motion model.
Group project for CS256 Spring 2022 @sjsu || Optimized and implemented unofficial version of one-shot free view neural talking head for live video conferencing.
Repository for the project for "Machine learning with limited supervision". This project develops a generative model for transferring motion from a video to a picture.
Evaluation pipeline for portrait animation models.
AI 虚拟人物换装 + 动作迁移 pipeline。in PNG + MP4 → out 成品视频 MP4 + JSON 日志
Containing several tutorials/demo about malicious uses and abuses of Artificial Intelligence used in the FIT3183 unit (Monash Malaysia, 2020).
[CVPR 2026] Official PyTorch implementation of "FlowMotion: Training-Free Flow Guidance for Video Motion Transfer"
Official implementation of the paper "Now You See Me, Now You Don’t: A Unified Framework for Expression-Consistent Video Anonymization."
[ECCV 2022] Motion Transformer for Unsupervised Image Animation
eMotion-GAN
Pi0-VLA Repository of "MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies"
OmniTransfer implementation for LTX-2 (work in progress)
Graduation Project repo. for Bachelor of Science degree in Computer Engineer, Cairo University, Egypt.
[AAAI 2024] Continuous Piecewise-Affine Based Motion Model for Image Animation
Official Repository of “MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies"
Real-time human pose detection and motion transfer to 3D avatars using MediaPipe, DNN, and Three.js — supports webcam and video inputs with custom avatar integration.
Add a description, image, and links to the motion-transfer topic page so that developers can more easily learn about it.
To associate your repository with the motion-transfer topic, visit your repo's landing page and select "manage topics."