构建大规模光照数据集与生成模型，实现精准可控的人脸重光照。
POLAR: A Portrait OLAT Dataset and Generative Framework for Illumination-Aware Face Modeling
- 采集200+人物在156种光照方向下的多视角表情数据。
- 提出流模型POLARNet，单图预测各光源响应，还原精细光照效果。
- 物理可解释的连续光照变换，适合影视特效与虚拟人应用。
人脸重光照旨在合成新光照条件下的逼真肖像，同时保持身份和几何特征。然而，进展受限于大规模、物理一致光照数据的匮乏。为此，我们提出POLAR，一个大规模、物理校准的单光照逐次（OLAT）数据集，包含超过200名被试，在156个光照方向下，涵盖多视角和多样表情。基于POLAR，我们开发了基于流的生成模型POLARNet，能够从单张肖像中预测每束光的OLAT响应，捕捉细微且方向感知的光照效应，同时保持面部身份不变。与依赖统计或上下文线索的扩散或背景条件方法不同，我们的方法将光照建模为光照状态间的连续、物理可解释变换，实现可扩展、可控制的重光照。POLAR与POLARNet共同构成统一的光照学习框架，连接真实数据、生成合成与物理基础重光照，建立可持续的“鸡生蛋”循环，推动可扩展、可复现的人脸光照建模。项目主页：https://rex0191.github.io/POLAR/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。