Reproduce “Shared-Factor-Conditioned Diffusion for Low-Rank Tensor Recovery” 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

Zhengyun Cheng, Guanwen Zhang, Wei Zhou

DiffTR presents a tensor recovery framework for completion, denoising, and hyperspectral image super-resolution. It learns coordinate-conditioned feature vectors and a diffusion score network, while task-specific observation constraints guide recovery. For hyperspectral image super-resolution, low-resolution hyperspectral data trains the representation and higher-resolution multispectral measurements guide sampling. In the noiseless benchmark, it leads in 8 of 15 settings, with exceptions.

Summary by alphaXiv.

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