Reproduce “Direct Conditional Parameterization for N-Dimensional Splatting” 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
Zhongpai Gao, Benjamin Planche, Van Nguyen Nguyen, Meng Zheng, Anwesa Choudhuri, Arun Innanje, Terrence Chen, Ziyan Wu
The authors directly parameterize N-dimensional splatting, storing rendering-aligned quantities rather than deriving them from joint covariances at each query. Their dGS and dBS methods use controls for position and opacity with Gaussian and Beta kernels. On 7DGS-PBR, dBS raises mean PSNR from 30.61 to 31.87 dB and fused-CUDA throughput from 396.33 to 539.57 FPS; evidence covers five datasets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.