Deep Light Pollution Removal in Night Cityscape Photographs

2026-04-10

AI Summary

This study addresses the challenge of light pollution in urban night photography, where artificial illumination obscures the night sky and introduces halo and glow artifacts. The work proposes a physics-driven degradation model that incorporates an anisotropic diffusion process to account for directional light sources and explicitly models skyglow caused by unseen sources below the horizon. To overcome the scarcity of paired real-world data, the authors introduce a joint training strategy that couples synthetic data with real images, leveraging generative foundation models to achieve high-quality restoration. Experimental results demonstrate that the proposed method effectively suppresses light pollution artifacts and significantly outperforms existing approaches in recovering natural night-sky appearance and enhancing the visibility of stellar details.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Adversarial Learning & Robustness
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Nighttime photography is severely degraded by light pollution induced by pervasive artificial lighting in urban environments. After long-range scattering and spatial diffusion, unwanted artificial light overwhelms natural night luminance, generates skyglow that washes out the view of stars and celestial objects and produces halos and glow artifacts around light sources. Unlike nighttime dehazing, which aims to improve detail legibility through thick air, the objective of light pollution removal is to restore the pristine night appearance by neutralizing the radiative footprint of ground lighting. In this paper we introduce a physically-based degradation model that adds to the previous ones for nighttime dehazing two critical aspects; (i) anisotropic spread of directional light sources, and (ii) skyglow caused by invisible surface lights behind skylines. In addition, we construct a training strategy that leverages large generative model and synthetic-real coupling to compensate for the scarcity of paired real data and enhance generalization. Extensive experiments demonstrate that the proposed formulation and learning framework substantially reduce light pollution artifacts and better recover authentic night imagery than prior nighttime restoration methods.

Problem

• light pollution
• night cityscape
• skyglow
• artificial lighting
• nighttime photography

Innovation

• light pollution removal
• physically-based degradation model
• anisotropic light diffusion
• skyglow modeling
• synthetic-real coupling