Reproduce “Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus” 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
Zhuofeng Wu, Yusuke Monno, Masatoshi Okutomi
The authors estimate depth from images captured at different focus settings by learning location-dependent point spread functions from real sharp and blurred image pairs. Their depth network also receives each location’s distance from the image center, using a rotational-symmetry model. On 60 real one-plane scenes, DualDfD’s MAE falls from 0.2351 to 0.0503; units are unspecified, and broader real-world depths remain untested.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.