Reproduce “Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization” 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
You Shen, Zhipeng Zhang, Xinyang Li, Yansong Qu, Yu Lin, Shengchuan Zhang, Liujuan Cao
CarGS builds one Gaussian-splatting model for novel-view rendering and surface reconstruction, separating rendering covariance from a learned geometry adjustment. Lite-Geo uses a residual covariance, while geometry-guided densification adds primitives using normal mismatch and SDF distance. On six Tanks and Temples scenes, CarGS ties mean F1 at 0.50 and leads mean PSNR at 26.01, with metric- and scene-specific exceptions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.