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
Качество дополнительной фотографии портретов смартфонов становится все более важным для производителей и пользователей. Последние устройства используют сложные вычислительные трубопроводы для улучшения рендеринга лица при разнообразном освещении. Эти трубопроводы широко варьируются между производителями, поэтому один и тот же портрет может выглядеть заметно по-разному по смартфонам. Эти различия влияют на несколько аспектов внешнего вида лица, делая перцептивные предпочтения сложными для характеристики с помощью одной меры. Чтобы решить этот вопрос, мы предлагаем интерпретируемую структуру, которая разлагает контраст лица на три компонента: общее тональное разделение лица, контраст глаз-регион и микроконтраст тонких деталей кожи. Мы формулируем специальные метрики для каждого компонента
Machine translation (Meta M2M100); the English original follows.
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
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26517, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange