Presentation

<
RaDe-GS: Rasterizing Depth in Gaussian Splatting
SessionGaussian Reconstruction
DescriptionGaussian Splatting enables high-quality, real-time novel-view synthesis, but extracting detailed 3D geometry remains challenging. We introduce a rasterized approach to render the depth and normal maps for general 3D Gaussian primitives. Our method significantly enhances shape reconstruction accuracy while maintaining the computational efficiency of Gaussian Splatting.
Authors
Baowen Zhang
Hong Kong University of Science and Technology
Chuan Fang
Hong Kong University of Science and Technology
Rakesh Shrestha
Simon Fraser University
Yixun Liang
Hong Kong University of Science and Technology
xiaoxiao Long
Nanjing University
Ping Tan
Hong Kong University of Science and Technology
Presenter
Baowen Zhang
Hong Kong University of Science and Technology
Event Type
Technical Paper
TimeThursday, 23 July 20264:25pm - 4:35pm PDT
LocationRoom 408 B
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20263:45pm - 5:15pm PDTRoom 408 B
Keywords
Geometry
Modeling
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationGaussian Reconstruction - Interactive Discussion
Similar Presentations
Learning View-Dependent Splatting Kernels
SHARP-GS: Scalable High-fidelity Accelerated Rendering Pipeline for Ultra-high Resolution 3D Gaussian Splatting
Ref-DGS: Reflective Dual Gaussian Splatting