-
AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars
AvatarCLIP is a zero-shot text-driven 3D avatar generation and animation pipeline. -
DreamWaltz dataset
The dataset used in the paper for training and testing the DreamWaltz framework for generating and animating complex 3D avatars from text guidance and parametric human body prior. -
Sprites dataset
The dataset consists of binary images of sprites with variations in the shape (oval, square, and heart) and four geometric factors: scale (6 variation modes), rotation (40), and...