Presentation
ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions
SessionAvatars
DescriptionScaffoldAvatar presents a novel approach for reconstructing ultra-high fidelity animatable head avatars, which can be rendered in real-time. Our method operates on patch-based local expression features and synthesizes 3D Gaussians dynamically by leveraging tiny scaffold MLPs. We employ color-based densification and progressive training to obtain high-quality results and fast convergence.
Event Type
Technical Paper
TimeWednesday, 13 August 202511:15am - 11:25am PDT
LocationWest Building, Rooms 220-222
ACM Digital Library
Journal Papers' PDFs
Conference 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
Not Livestreamed
Not Recorded
