Reproduce “Interpretable Face Contrast Modeling for Smartphone Portrait Rendering” 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
Yujin Cho, Benoît Pochon, Jean-Michel Morel, Gabriele Facciolo
The authors measure smartphone portrait contrast as three components: face-wide tonal separation, dark–bright separation in the eyes, and fine skin-detail visibility. The measures use normalized lightness and region masks, and are evaluated against expert pairwise judgments. For devices held out under fixed lighting, overall contrast correlates better with judgments than Michelson contrast, but evidence is mainly from mannequins.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.