Differentiable Surface Splatting for Point-based Geometry Processing

 

We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds.

November 1, 2019
ACM SIGGRAPH Asia 2019

 

Authors

Yifan Wang (ETH Zurich)

Serena Felice (ETH Zurich)

Wu Shihao (ETH Zurich)

Cengiz Oztireli (DisneyResearch|Studios)

Olga Sorkine-Hornung (ETH Zurich)

 

Differentiable Surface Splatting for Point-based Geometry Processing

Abstract

We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds. Gradients for point locations and normals are carefully designed to handle discontinuities of the rendering function. Regularization terms are introduced to ensure uniform distribution of the points on the underlying surface. We demonstrate applications of DSS to inverse rendering for geometry synthesis and denoising, where large scale topological changes as well as small scale detail modifications are accurately and robustly handled without requiring explicit connectivity, outperforming state-of-the-art techniques.

Copyright Notice