Presentation

<
DiffPoseTalk: Speech-driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models
Session3D Face Generator and Animation
DescriptionDiffPoseTalk introduces a novel diffusion-based system for generating speech-driven facial animations and head poses, featuring example-based style control through contrastive learning. It overcomes the scarcity of 3D talking face data by utilizing reconstructed 3DMM parameters from a newly developed audio-visual dataset, enabling the generation of diverse and stylistic motions.
Authors
Zhiyao Sun
Tsinghua University
Tian Lv
Tsinghua University
Sheng Ye
Tsinghua University
Matthieu Lin
Tsinghua University
Jenny Sheng
Tsinghua University
Yu-Hui Wen
Beijing Jiaotong University
Minjing Yu
Tianjin University
Yong-Jin Liu
Tsinghua University
Event Type
Technical Paper
TimeMonday, 29 July 202411:15am - 11:25am MDT
LocationMile High 1
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 202410:45am - 12:15pm MDTMile High 1
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation
Geometry
Modeling
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationS3: Speech, Script, and Scene Driven Head and Eye Animation