WildRelight：一個真實世界基準與物理引導自適應之單一影像重照明

WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting

May 12, 2026

作者: Lezhong Wang, Mehmet Onurcan Kaya, Siavash Bigdeli, Jeppe Revall Frisvad

cs.AI

摘要

近年来，基于先进生成模型的单图像重光照方法在合成基准测试中已实现令人惊艳的逼真效果。然而，其在真实世界复杂视觉场景中的有效性仍缺乏系统验证。当前数据集通常针对多视角重建设计，未能针对单图像重光照的独特挑战，这构成了关键研究空白。为弥合合成数据与真实场景之间的鸿沟，我们提出WildRelight——首个专为评估单图像重光照模型而构建的真实野外数据集。该数据集收录了多样化的高分辨率室外场景，在严格对齐、随时间变化的自然光照条件下采集，并配以高动态范围环境贴图。借助该数据，我们建立了严苛的基准测试，揭示出当前基于合成数据训练的先进模型存在严重域偏移。WildRelight中严格对齐的时间序列结构为域适应开辟了新范式。我们通过引入物理引导的推理框架加以证明——该框架将捕获的自然光演变作为自监督约束。通过将扩散后验采样（DPS）与时间感知的测试时自适应（TTA）相结合，我们展示该数据集可让合成模型即时对齐真实世界统计规律，将棘手的模拟到真实迁移挑战转化为可处理的自监督任务。数据集与代码将开源，以推动鲁棒的、基于物理的重光照研究。

English

Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world remains largely unverified. A critical gap exists, as current datasets are typically designed for multi-view reconstruction and fail to address the unique challenges of single-image relighting. To bridge this synthetic-to-real gap, we introduce WildRelight, the first in-the-wild dataset specifically created for evaluating single-image relighting models. WildRelight features a diverse collection of high-resolution outdoor scenes, captured under strictly aligned, temporally varying natural illuminations, each paired with a high-dynamic-range environment map. Using this data, we establish a rigorous benchmark revealing that state-of-the-art models trained on synthetic data suffer from severe domain shifts. The strictly aligned temporal structure of WildRelight enables a new paradigm for domain adaptation. We demonstrate this by introducing a physics-guided inference framework that leverages the captured natural light evolution as a self-supervised constraint. By integrating Diffusion Posterior Sampling (DPS) with temporal Sampling-Aware Test-Time Adaptation (TTA), we show that the dataset allows synthetic models to align with real-world statistics on-the-fly, transforming the intractable sim-to-real challenge into a tractable self-supervised task. The dataset and code will be made publicly available to foster robust, physically-grounded relighting research.