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

Source: https://huggingface.co/papers/2605.11696

Abstract

WildRelight dataset addresses the gap between synthetic and real-world single-image relighting by providing high-resolution outdoor scenes with aligned natural illumination, enabling physics-guided domain adaptation through diffusion posterior sampling and test-time adaptation.

Recentsingle-image relightingmethods, powered by advancedgenerative 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 ofsingle-image relighting. To bridge this synthetic-to-real gap, we introduce WildRelight, the first in-the-wild dataset specifically created for evaluatingsingle-image relightingmodels. 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 severedomain shifts. The strictly aligned temporal structure of WildRelight enables a new paradigm for domain adaptation. We demonstrate this by introducing aphysics-guided inferenceframework that leverages the captured natural light evolution as a self-supervised constraint. By integratingDiffusion Posterior Sampling(DPS) withtemporal 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.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.11696

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.11696 in a model README.md to link it from this page.

Datasets citing this paper1

#### Lez/wildrelight Updatedabout 2 hours ago • 97 • 1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.11696 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.