Presentation

<
LAM: Large Avatar Model for One-shot Animatable Gaussian Head
SessionGet a Head
DescriptionLAM is an innovative Large Avatar Model for animatable Gaussian head reconstruction from a single image in seconds. Our Gaussian heads are immediately animatable and renderable without additional networks or post-processing. This allows seamless integration into existing rendering pipelines, ensuring real-time animation and rendering across various platforms, including mobile phones.
Authors
Yisheng He
Alibaba Group
Xiaodong Gu
Alibaba Group
Xiaodan Ye
Alibaba Group
Chao Xu
Alibaba Group
Zhengyi Zhao
Alibaba Group
Yuan Dong
Alibaba Group
Weihao Yuan
Alibaba Group
Zilong Dong
Alibaba Group
Liefeng Bo
Alibaba Group
Event Type
Technical Paper
TimeMonday, 11 August 20252:20pm - 2:30pm PDT
LocationWest Building, Rooms 301-305
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Monday, 11 August 20252:00pm - 3:30pm PDTWest Building, Rooms 301-305
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationSOAP: Style-Omniscient Animatable Portraits
Similar Presentations
Emerging Technologies Demo - LAM: Large Avatar Model for One-Shot Animatable Gaussian Head
Text-based Animatable 3D Avatars with Morphable Model Alignment
TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling