Fa-Ting Hong

awesome-talking-head-generation.

CVPR2022-DaGAN. Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

ACTalker. ICCV 2025 ACTalker: an end-to-end video diffusion framework for talking head synthesis that supports both single and multi-signal control (e.g., audio, expression).

ICCV2023-MCNET. The official code of our ICCV2023 work: Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation

MM2021-CO2-Net. Python

Face-Depth-Network. The component of DaGAN (CVPR 2022)

POINT. Code for CVPR2019 "Learning to Learn Relation for Important People Detection in Still Images "

FVHuman. The CVPR 2025 Highlight official implementation of "Free-viewpoint Human Animation with Pose-correlated Reference Selection"

video-evaluation-toolkit. Video Evaluation, PSNR, SSM, LPIPS, VBENCH

opencvTest1. C++

UniAnimate. Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

synthdata-zh. synthdata-zh is a project that generates a Chinese language training set

Dive-into-DL-PyTorch. 本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

CVPR2020-Semi-Point. Python

harlanhong.github.io. HTML

articulated-animation. Code for Motion Representations for Articulated Animation paper

magic-animate. MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

sibyl-research-system. Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code