Full Dynamic Range Sky-Modelling For Image Based Lighting

2026-03-05

AI Summary

Existing deep learning–based sky models struggle to accurately reconstruct illumination in the solar region of high dynamic range (HDR) skies exceeding 14 EV, leading to distortions in image-based lighting (IBL), such as inaccurate shadows and unrealistic color tones. To address this limitation, this work proposes Icarus, an all-weather sky modeling method that achieves the first accurate reconstruction of full HDR sky illumination. Built upon a deep conditional generative network, Icarus is trained on real-world full dynamic range (FDR) images and integrates physical lighting constraints with user-guided controls, enabling flexible specification of sun position, cloud distribution, and atmospheric texture. Experiments demonstrate that Icarus significantly outperforms existing approaches in lighting accuracy, shadow directionality, color fidelity, and visual realism, offering a high-quality, general-purpose alternative for environmental illumination.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Accurate environment maps are a key component to modelling real-world outdoor scenes. They enable captivating visual arts, immersive virtual reality and a wide range of scientific and engineering applications. To alleviate the burden of physical-capture, physically-simulation and volumetric rendering, sky-models have been proposed as fast, flexible, and cost-saving alternatives. In recent years, sky-models have been extended through deep learning to be more comprehensive and inclusive of cloud formations, but recent work has demonstrated these models fall short in faithfully recreating accurate and photorealistic natural skies. Particularly at higher resolutions, DNN sky-models struggle to accurately model the 14EV+ class-imbalanced solar region, resulting in poor visual quality and scenes illuminated with skewed light transmission, shadows and tones. In this work, we propose Icarus, an all-weather sky-model capable of learning the exposure range of Full Dynamic Range (FDR) physically captured outdoor imagery. Our model allows conditional generation of environment maps with intuitive user-positioning of solar and cloud formations, and extends on current state-of-the-art to enable user-controlled texturing of atmospheric formations. Through our evaluation, we demonstrate Icarus is interchangeable with FDR physically captured outdoor imagery or parametric sky-models, and illuminates scenes with unprecedented accuracy, photorealism, lighting directionality (shadows), and tones in Image Based Lightning (IBL).

Problem

• Full Dynamic Range
• sky-model
• Image Based Lighting
• photorealism
• solar region

Innovation

• Full Dynamic Range
• Image Based Lighting
• sky modeling
• deep learning
• photorealistic rendering