{"ID":2828897,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.13192","arxiv_id":"2512.13192","title":"POLAR: A Portrait OLAT Dataset and Generative Framework for Illumination-Aware Face Modeling","abstract":"Face relighting aims to synthesize realistic portraits under novel illumination while preserving identity and geometry. However, progress remains constrained by the limited availability of large-scale, physically consistent illumination data. To address this, we introduce POLAR, a large-scale and physically calibrated One-Light-at-a-Time (OLAT) dataset containing over 200 subjects captured under 156 lighting directions, multiple views, and diverse expressions. Building upon POLAR, we develop a flow-based generative model POLARNet that predicts per-light OLAT responses from a single portrait, capturing fine-grained and direction-aware illumination effects while preserving facial identity. Unlike diffusion or background-conditioned methods that rely on statistical or contextual cues, our formulation models illumination as a continuous, physically interpretable transformation between lighting states, enabling scalable and controllable relighting. Together, POLAR and POLARNet form a unified illumination learning framework that links real data, generative synthesis, and physically grounded relighting, establishing a self-sustaining \"chicken-and-egg\" cycle for scalable and reproducible portrait illumination. Our project page: https://rex0191.github.io/POLAR/.","short_abstract":"Face relighting aims to synthesize realistic portraits under novel illumination while preserving identity and geometry. However, progress remains constrained by the limited availability of large-scale, physically consistent illumination data. To address this, we introduce POLAR, a large-scale and physically calibrated...","url_abs":"https://arxiv.org/abs/2512.13192","url_pdf":"https://arxiv.org/pdf/2512.13192v2","authors":"[\"Zhuo Chen\",\"Chengqun Yang\",\"Zhuo Su\",\"Zheng Lv\",\"Jingnan Gao\",\"Xiaoyuan Zhang\",\"Xiaokang Yang\",\"Yichao Yan\"]","published":"2025-12-15T11:04:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}