Reproduce “3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yixiao Yang, Yu-Shen Liu, Zhizhong Han

The method improves 3D Gaussian Splatting geometry by predicting view-dependent color with a smooth neural field and training it using posed images and spatial samples derived from rendered depth. On DTU, mean Chamfer Distance falls from 1.92 to 1.13 for the 3DGS backbone. Gains are smaller for PGSR, while training time and rendering computation increase. Outdoor geometry remains unverified.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.