Reproduce “CaliSplat: Sparse Gaussian Fitting and Calibrated Rate Allocation for Image Compression” 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

Zhenbang Zhang, Zhengquan Luo, Kai Zhao, Zhiqiang Xu

CaliSplat reduces fitting effort for per-image Gaussian compression by using one-color block error to screen candidate fits, then calibrating distortions and allocating a limited Gaussian budget across regions. In the paper’s nine-image large-image dataset group, at the high-rate point, it reaches 31.86 dB PSNR versus SGI’s 30.55 dB, with lower fitting time. This result is limited to that dataset and rate.

Summary by alphaXiv.

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