Presentation

<
GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering
SessionStabilize and Personalize Your Pixels
DescriptionGaVS: Transform unstable shaky videos into smooth, professional-quality footage. We design novel 3D rednering technology that preserves the motion intent while eliminating shakes and distortions—no cropping, no distortion and workable under dynamics and intense motions. GaVS delivers natural-looking results validated by users as superiority. Capture life steadily!
Authors
Zinuo You
ETH Zürich
Huawei Research Zürich
Stamatios Georgoulis
Huawei Research Zürich
Anpei Chen
ETH Zürich
University of Tuebingen
Siyu Tang
ETH Zürich
Dengxin Dai
Huawei Research Zürich
Event Type
Technical Paper
TimeMonday, 11 August 20259:10am - 9:20am PDT
LocationWest Building, Rooms 118-120
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 20259:00am - 10:30am PDTWest Building, Rooms 118-120
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationNested Attention: Semantic-aware Attention Values for Concept Personalization
Similar Presentations
ColorSurge: Bringing Vibrancy and Efficiency to Automatic Video Colorization via Dual-Branch Fusion
4D Gaussian Videos with Motion Layering
Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing