Presentation

<
SqueezeMe: Mobile-Ready Distillation of Gaussian Full-Body Avatars
SessionAvatars
DescriptionExisting Gaussian Splatting avatars require desktop GPUs, limiting mobile device use. SqueezeMe converts these avatars into a lightweight representation, enabling real-time animation and rendering on mobile devices. By distilling the corrective decoder into an efficient linear model, SqueezeMe achieves 72 FPS on a Meta Quest 3 VR headset.
Authors
Forrest Iandola
Meta
Stanislav Pidhorskyi
Meta
Igor Santesteban
Meta
Divam Gupta
Meta
Anuj Pahuja
Meta
Nemanja Bartolovic
Meta
Frank Yu
Meta
Emanuel Garbin
Meta
Tomas Simon
Meta
Shunsuke Saito
Meta
Event Type
Technical Paper
TimeWednesday, 13 August 202511:25am - 11:35am PDT
LocationWest Building, Rooms 220-222
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 202510:45am - 12:15pm PDTWest Building, Rooms 220-222
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Registration Categories
Full Conference
Virtual Access
Wednesday
Next PresentationNext PresentationTransforming Unstructured Hair Strands into Procedural Hair Grooms
Similar Presentations
Relightable Full-Body Gaussian Codec Avatars
AI-Powered Real-Time VFX for Mobile
LAM: Large Avatar Model for One-shot Animatable Gaussian Head