Reproduce “Learning Lens Blur Fields” 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

Esther Y. H. Lin, Zhecheng Wang, Rebecca Lin, Daniel Miau, Florian Kainz, Jiawen Chen, Xuaner Cecilia Zhang, David B. Lindell and 1 more

The authors fit a continuous neural field to known monitor patterns photographed at different focus settings, predicting camera blur across sensor position, kernel offset, and focus. In two tested iPhone 14 Pro wide cameras, repeated-capture variation was smaller than between-camera differences. The method depends on known calibration patterns and does not establish general device identification or blind blur estimation.

Summary by alphaXiv.

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