WildRelight：面向单图像重光照的真实世界基准与物理引导自适应

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了令人印象深刻的真实感效果。然而，它们在真实世界复杂视觉场景中的有效性仍未得到充分验证。当前数据集通常专为多视角重建设计，未能解决单图像重光照的独特挑战，这一关键空白亟待填补。为弥合合成与真实之间的鸿沟，我们提出WildRelight——首个专门用于评估单图像重光照模型的野外数据集。WildRelight包含多样化的高分辨率户外场景，在严格对齐且随时间变化的自然光照条件下捕获，每个场景均配以高动态范围环境贴图。利用这些数据，我们建立了严格的基准测试，揭示出基于合成数据训练的先进模型存在严重的领域偏移问题。WildRelight严格对齐的时间结构为领域自适应提供了新范式。我们通过引入物理引导的推理框架来证明这一点，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与时间感知的测试时自适应相结合，我们展示了该数据集能够使合成模型实时对齐真实世界统计特性，将棘手的仿真到真实挑战转化为可处理的自监督任务。该数据集及代码将公开提供，以促进鲁棒且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.