Reproduce “Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing” 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

Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Jiajun Shen, Jia Li, Xiaojuan Qi

ESDNet addresses moiré artifacts in screen photographs by combining multiple artifact scales within each network stage and adapting their weights to each image. On UHDM, a benchmark of 5,000 screen-photographed image pairs, it reaches 22.119 dB PSNR versus 20.338 dB for FHDe²Net. This comparison applies to the paper’s 4K evaluation setup, not phone performance.

Summary by alphaXiv.

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