Presentation

<
Learning View-Dependent Splatting Kernels
Session3D Gaussian Splatting II
DescriptionWe present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis.
Authors
Huakeng Ding
State Key Lab of CAD and CG, Zhejiang University
Zhanpeng Liu
State Key Lab of CAD and CG, Zhejiang University
Fan Pei
State Key Lab of CAD and CG, Zhejiang University
Kun Zhou
State Key Lab of CAD and CG, Zhejiang University
Hongzhi Wu
State Key Lab of CAD and CG, Zhejiang University
Event Type
Technical Paper
TimeThursday, 23 July 20262:20pm - 2:30pm PDT
LocationRoom 408 A
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20262:00pm - 3:30pm PDTRoom 408 A
Keywords
Geometry
Modeling
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationCAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation
Similar Presentations
Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
HairGPT: A Unified Autoregressive Framework for 3D Realistic Hairstyle Synthesis
Neural Cellular Automata: From Cells to Pixels