Reproduce “Gaussian Material Fields for Volumetric Multi-Energy CT Decomposition” 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

Jian Lin, Jiancheng Fang, Hongming Shan, Shaoyu Wang, Yang Chen, Qiegen Liu

Gaussian material fields reconstruct multi-energy CT material maps by sharing anisotropic 3D Gaussian geometry while assigning each material independent nonnegative coefficients. They fit projections with a calibrated linear basis model and adaptively refine shared spatial support. Across 15 simulated-projection cases, they average 36.18 dB PSNR, 0.9305 SSIM, and 0.0193 NRMSE, versus 32.15 dB, 0.8865, and 0.0290 for the strongest baseline; these are not clinical-scan results.

Summary by alphaXiv.

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