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

Portuguese

A qualidade da fotografia de retrato do smartphone tornou-se cada vez mais importante para os fabricantes e usuários. Os dispositivos recentes usam pipelines computacionais complexos para melhorar a renderização facial sob iluminação variada. Esses pipelines variam amplamente entre os fabricantes, de modo que o mesmo retrato pode parecer significativamente diferente entre os smartphones. Essas diferenças afetam vários aspectos da aparência facial, tornando as preferências perceptivas difíceis de caracterizar com uma única medida. Para abordar isso, propomos um quadro interpretável que decompõe o contraste facial em três componentes: separação tonal geral do rosto, contraste olho-região e micro-contraste de detalhes finos da pele. Formulamos métricas dedicadas para cada componente e as validamos por pares de julgamentos humanos,

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