Reproduce “Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography Reconstruction” 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
Taewon Yang, Jason Hu, Jeffrey A. Fessler, Liyue Shen
The method reconstructs sparse-view 3D CT by training a 3D denoiser on local patches conditioned on a downsampled whole volume and patch coordinates, combining local detail with global context. On one LIDC-IDRI 256×256×256 test volume with 20 views, it reaches 38.56 dB PSNR versus 37.05 dB for fine-tuned DiffusionBlend; this benchmark result does not establish clinical readiness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.