Newest papers

Interpretable Face Contrast Modeling for Smartphone Portrait Rendering

Yujin Cho, Benoit Pochon, Jean‐Michel Morel, Gabriele Facciolo · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26517 · cited by 0 works (OpenAlex) · open-access PDF

French

La qualité de la photographie de portrait de smartphone est devenue de plus en plus importante pour les fabricants et les utilisateurs. Les appareils récents utilisent des pipelines de calcul complexes pour améliorer le rendu du visage sous un éclairage varié. Ces pipelines varient largement entre les fabricants, de sorte que le même portrait peut paraître sensiblement différent entre les smartphones. Ces différences affectent plusieurs aspects de l'apparence faciale, ce qui rend la préférence perceptuelle difficile à caractériser avec une seule mesure. Pour y remédier, nous proposons un cadre interprétable qui décompose le contraste du visage en trois composants: séparation tonale globale du visage, contraste œil-région et micro-contraste des détails de la peau fine. Nous formulons des mesures dédiées pour chaque

Machine translation (Meta M2M100); the English original follows.

Abstract

The quality of smartphone portrait photography has become increasingly important to both manufacturers and users. Recent devices use complex computational pipelines to improve facial rendering under varied lighting. These pipelines vary widely across manufacturers, so the same portrait can look noticeably different across smartphones. These differences affect multiple aspects of facial appearance, making perceptual preference difficult to characterize with a single measure. To address this, we propose an interpretable framework that decomposes face contrast into three components: overall facial tonal separation, eye-region contrast, and micro-contrast of fine skin details. We formulate dedicated metrics for each component and validate them via pairwise human judgments, demonstrating that our approach correlates more closely with human contrast perception than traditional contrast measures. To support this analysis, we introduce a realistic mannequin-based dataset designed for systematic facial contrast evaluation, comprising 508 full-resolution captures from 29 smartphones under diverse lighting, with region-specific masks and extensive pairwise perceptual annotations. As a downstream analysis, we show that combining the three component-wise metrics provides a meaningful basis for modeling balanced facial contrast preference in a controlled setting, and we present a preliminary evaluation on a smaller real-portrait dataset indicating that insights derived from the mannequin study can extend to real images. Our work provides a controlled first step toward defining and evaluating face contrast in portrait imaging.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Rendering (computer graphics), Contrast (vision), Artificial intelligence, Pairwise comparison, Perception

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange