Presentation

<
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
SessionDynamic Radiance Fields
DescriptionWe present a novel framework, GaussianPrediction, for forecasting future scenarios in dynamic scenes. GaussianPrediction employs a 3D Gaussian canonical space with deformation modeling and lifecycle property to represent changes effectively. Additionally, a novel concentric motion distillation technique with key points simplifies complex scene motion prediction with a GCN.
Authors
Boming Zhao
State Key Laboratory of CAD & CG, Zhejiang University
Yuan Li
State Key Laboratory of CAD & CG, Zhejiang University
Ziyu Sun
Jilin University
Lin Zeng
State Key Laboratory of CAD & CG, Zhejiang University
Yujun Shen
Ant Group
Rui Ma
Jilin University
Yinda Zhang
Google
Hujun Bao
State Key Laboratory of CAD & CG, Zhejiang University
Zhaopeng Cui
State Key Laboratory of CAD & CG, Zhejiang University
Event Type
Technical Paper
TimeWednesday, 31 July 20242:10pm - 2:20pm 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
Wednesday, 31 July 20242:00pm - 3:30pm MDTMile High 1
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Wednesday
Next PresentationNext PresentationFactorized Motion Fields for Fast Sparse Input Dynamic View Synthesis