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

• URL: http://arxiv.org/abs/2605.11696v1
• Date: Tue, 12 May 2026 07:53:27 GMT
• Title: WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
• Abstract summary: We introduce WildRelight, the first in-the-wild dataset specifically created for evaluating single-image relighting models.<n>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.
• Score: 1.4145309506833206
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination [0.0]
  This paper presents a systematic study analyzing the impact of lighting configurations and background complexity on object detection performance.<n>Through 18 controlled experiments utilizing a state-of-the-art YOLOv12 framework, we demonstrate that complex, indirect lighting configurations paired with domain-relevant background variability significantly increase visual cue richness.<n>Our findings show that avoiding direct specular peaks preserves crucial surface textures, mitigates the domain gap, reduces false positives, and accelerates model convergence compared to using conventional direct-light synthetic data.
  arXiv  Detail & Related papers  (2026-06-21T16:21:34Z)
• Learning a Delighting Prior for Facial Appearance Capture in the Wild [34.89149093909672]
  We propose to shift the paradigm into training a powerful delighting network as a prior to constrain the optimization.<n>By conditioning the core network on learnable source-aware tokens, we decouple dataset-specific styles from physical delighting principles.<n>We transform the multi-view NeRSemble dataset into NeRSemble-Scan, a large-scale collection of 4K-resolution relightable scans.
  arXiv  Detail & Related papers  (2026-05-07T03:43:24Z)
• Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion [17.59278811759214]
  We present a paradigm that fuses the specialized strengths of synthetic, One-Light-at-A-Time (OLAT), and real-world datasets into a compact model.<n>Our approach features specialized prior models hardened by domain-aware adaptation, followed by augmented knowledge distillation into a lightweight student model.<n>We construct a massive, high-fidelity synthetic dataset with diverse ground-truth intrinsics to support our training pipeline.
  arXiv  Detail & Related papers  (2026-04-25T01:16:11Z)
• PRISM: Rethinking Scattered Atmosphere Reconstruction as a Unified Understanding and Generation Model for Real-world Dehazing [22.670768613999787]
  PRISM is a physically structured framework that jointly reconstructs the clear scene and scattering variables under the atmospheric scattering model.<n>We design an online non-uniform haze synthesis pipeline and a Selective Self-distillation Adaptation scheme for unpaired real-world scenarios.<n>Experiments on real-world benchmarks demonstrate that PRISM achieves state-of-the-art performance on RID tasks.
  arXiv  Detail & Related papers  (2026-04-08T13:01:30Z)
• Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis [65.19146708498346]
  Atmospheric turbulence significantly degrades long-range imaging by introducing geometric warping and exposure-timedependent blur.<n>Existing methods for turbulence effects often oversimplify the relationship between blur and exposure-time.<n>We construct ET-Turb, a large-scale synthetic turbulence dataset that explicitly incorporates continuous exposure-time modeling.
  arXiv  Detail & Related papers  (2026-03-02T02:58:44Z)
• Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views [82.15089065452081]
  We present Relightable Holoported Characters (RHC), a person-specific method for free-view rendering and relighting of full-body and highly dynamic humans.<n>Our transformer-based RelightNet predicts relit appearance within a single network pass, avoiding costly OLAT-basis capture and generation.<n>Experiments demonstrate our method's superior visual fidelity and lighting reproduction compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-11-29T00:17:34Z)
• LuxDiT: Lighting Estimation with Video Diffusion Transformer [66.60450792095901]
  Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics.<n>We propose LuxDiT, a novel data-driven approach that fine-tunes a video diffusion transformer to generate HDR environment maps conditioned on visual input.
  arXiv  Detail & Related papers  (2025-09-03T19:59:20Z)
• UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting [85.27994475113056]
  We introduce a general-purpose approach that jointly estimates albedo and synthesizes relit outputs in a single pass.<n>Our model demonstrates strong generalization across diverse domains and surpasses previous methods in both visual fidelity and temporal consistency.
  arXiv  Detail & Related papers  (2025-06-18T17:56:45Z)
• Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecture [0.7499722271664147]
  Single image scene relighting aims to generate a realistic new version of an input image so that it appears to be illuminated by a new target light condition. We propose two new datasets: a synthetic dataset with the ground truth of intrinsic components and a real dataset collected under laboratory conditions. Our method outperforms the state-of-the-art methods in performance, as tested on both existing datasets and our newly developed datasets.
  arXiv  Detail & Related papers  (2024-09-27T14:15:02Z)
• DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer [78.91753256634453]
  We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiables. In this work, we propose DIBR++, a hybrid differentiable which supports these effects by combining specularization and ray-tracing. Compared to more advanced physics-based differentiables, DIBR++ is highly performant due to its compact and expressive model.
  arXiv  Detail & Related papers  (2021-10-30T01:59:39Z)
• Crowdsampling the Plenoptic Function [56.10020793913216]
  We present a new approach to novel view synthesis under time-varying illumination from such data. We introduce a new DeepMPI representation, motivated by observations on the sparsity structure of the plenoptic function. Our method can synthesize the same compelling parallax and view-dependent effects as previous MPI methods, while simultaneously interpolating along changes in reflectance and illumination with time.
  arXiv  Detail & Related papers  (2020-07-30T02:52:10Z)
• Deep Lighting Environment Map Estimation from Spherical Panoramas [0.0]
  We present a data-driven model that estimates an HDR lighting environment map from a single LDR monocular spherical panorama. We exploit the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism.
  arXiv  Detail & Related papers  (2020-05-16T14:23:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.