Presentation

AvatarCLIP: Zero-shot Text-driven Generation and Animation of 3D Avatars
SessionTechnical Papers
Authors
Fangzhou Hong
Mingyuan Zhang
Liang Pan
Zhongang Cai
Lei Yang
Ziwei Liu
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
Virtual
Registration Categories
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Time
Location
DescriptionWe present AvatarCLIP, a zero-shot, text-driven framework for 3D avatar generation and animation. Taking advantage of the powerful vision-language model CLIP, AvatarCLIP empowers users to customize a 3D avatar with the desired shape and texture and drive the avatar with the described motions using solely natural languages.
Authors
Fangzhou Hong
Nanyang Technological University
Mingyuan Zhang
Nanyang Technological University
Liang Pan
Nanyang Technological University
Zhongang Cai
SenseTime
Lei Yang
SenseTime
Ziwei Liu
Nanyang Technological University