One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior, CVPRW 2024

Project_page_cvprw2024

Convolutional Autoencoders for Human Motion Infilling (Unofficial pytorch version implementation)

Implementation Landmark Detection Module from Fake It Till You Make It Face analysis in the wild using synthetic data alone

For real-time hand gesture learning and classification using Fuzzy_ARTMAP and tkinter GUI

various transition to target motion through condtional content latent space

Motion infilling into target content

ZSRGAN: Zero-shot Super-Resolution with Generative Adversarial Network(Pytorch)

GENERATION TO ONE ANOTHER DOMAIN: Audio ⟷ Image (Pytorch)

OSSL Class assignment

Toy Project(ing..)