Differentiable Surface Splatting for Point-based Geometry Processing

2019/06/30 by Wang Yifan, Felice Serena, Shihao Wu +2 · 5 citations
Computer Science · #cs.GR #cs.NE

paper · pdf · doi:10.1145/3355089.3356513

This version is contains camera-ready manuscript for SIGGRAPH Asia 2019

arxiv created 2019/09/03 · arxiv updated 2019/09/05

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. The data and code are at https://github.com/yifita/DSS.

Cited by

• When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering
• ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration
• Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding
• Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering
• CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting