Deep Light Pollution Removal in Night Cityscape Photographs

TL;DR

This paper presents a physically-based model and a novel training strategy to effectively remove light pollution from night cityscape photos, restoring natural night appearance.

Contribution

It introduces a new degradation model accounting for anisotropic light spread and skyglow, along with a training approach leveraging generative models for better generalization.

Findings

Significantly reduces light pollution artifacts in images.

Outperforms prior methods in restoring authentic night imagery.

Enhances generalization through synthetic-real data coupling.

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.