Deep Light Pollution Removal in Night Cityscape Photographs

• URL: http://arxiv.org/abs/2604.09145v1
• Date: Fri, 10 Apr 2026 09:23:37 GMT
• Title: Deep Light Pollution Removal in Night Cityscape Photographs
• Abstract summary: Nighttime photography is severely degraded by light pollution induced by pervasive artificial lighting in urban environments.<n>We introduce a physically-based degradation model that adds to the previous ones for nighttime dehazing.<n>We construct a training strategy that leverages large generative model and synthetic-real coupling to compensate for the scarcity of paired real data.
• Score: 17.074532372502038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model [113.62837263178346]
  In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings.<n>We propose an integration of an illumination-guided module embedded in the diffusion model to guide the illumination restoration process.<n>Our model can preserve texture fidelity while contending with the adversities posed by various degradation in low-light scenarios.
  arXiv  Detail & Related papers  (2026-05-14T04:01:41Z)
• The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception [58.895000127068194]
  We introduce the Diffusion-Based Nighttime Dehazing framework, which excels in both data synthesis and lighting reconstruction.<n>We propose a restoration model that integrates a pre-trained diffusion model guided by a brightness perception network.<n>Experiments validate our dataset's utility and the model's superior performance in joint haze removal and brightness mapping.
  arXiv  Detail & Related papers  (2025-06-03T03:21:13Z)
• Seeing Beyond Haze: Generative Nighttime Image Dehazing [16.949777020546264]
  BeyondHaze is a generative nighttime dehazing method that infers background information in regions where it may be absent.<n>Our approach is developed on two main ideas: gaining strong background priors by adapting image diffusion models to the nighttime dehazing problem, and enhancing generative ability for haze- and glow-obscured scene areas through guided training.<n>Experiments on real-world images demonstrate that BeyondHaze effectively restores visibility in dense nighttime haze.
  arXiv  Detail & Related papers  (2025-03-11T06:08:25Z)
• Night-to-Day Translation via Illumination Degradation Disentanglement [51.77716565167767]
  Night-to-Day translation aims to achieve day-like vision for nighttime scenes. processing night images with complex degradations remains a significant challenge under unpaired conditions. We propose textbfN2D3 to identify different degradation patterns in nighttime images.
  arXiv  Detail & Related papers  (2024-11-21T08:51:32Z)
• Sun Off, Lights On: Photorealistic Monocular Nighttime Simulation for Robust Semantic Perception [53.631644875171595]
  Nighttime scenes are hard to semantically perceive with learned models and annotate for humans. Our method, named Sun Off, Lights On (SOLO), is the first to perform nighttime simulation on single images in a photorealistic fashion by operating in 3D. Not only is the visual quality and photorealism of our nighttime images superior to competing approaches including diffusion models, but the former images are also proven more beneficial for semantic nighttime segmentation in day-to-night adaptation.
  arXiv  Detail & Related papers  (2024-07-29T18:00:09Z)
• From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement [22.565044107631696]
  Existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. These methods have limited exploration in another major visibility damage, the glow effects in real night scenes. We propose a new method for learning physical glow generation via multiple scattering estimation according to the Atmospheric Point Spread Function (APSF) The proposed method is based on zero-shot learning and does not rely on any paired or unpaired training data. Empirical evaluations demonstrate the effectiveness of the proposed method in both glow suppression and low-light enhancement tasks.
  arXiv  Detail & Related papers  (2023-07-31T15:51:15Z)
• NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer [39.90066556289063]
  We propose an end-to-end transformer-based framework for nighttime haze removal, called NightHazeFormer. Our proposed approach consists of two stages: supervised pre-training and semi-supervised fine-tuning. Experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods.
  arXiv  Detail & Related papers  (2023-05-16T15:26:09Z)
• Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior [81.64647648269889]
  Reflective flare is a phenomenon that occurs when light reflects inside lenses, causing bright spots or a "ghosting effect" in photos. We propose an optical center symmetry prior, which suggests that the reflective flare and light source are always symmetrical around the lens's optical center. We create the first reflective flare removal dataset called BracketFlare, which contains diverse and realistic reflective flare patterns.
  arXiv  Detail & Related papers  (2023-03-27T09:44:40Z)
• See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images [73.23687409870656]
  We propose a cycle generative adversarial network to construct a novel end-to-end image dehaze model. We adopt outdoor image datasets to train our model, which includes a set of real-world unpaired image dataset and a set of paired image dataset. Based on the cycle structure, our model adds four different kinds of loss function to constrain the effect including adversarial loss, cycle consistency loss, photorealism loss and paired L1 loss.
  arXiv  Detail & Related papers  (2022-10-14T07:45:33Z)
• Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression [67.7508230688415]
  We introduce an unsupervised method that integrates a layer decomposition network and a light-effects suppression network. Our method outperforms state-of-the-art methods in suppressing night light effects and boosting the intensity of dark regions.
  arXiv  Detail & Related papers  (2022-07-21T16:10:24Z)
• Light Pollution Reduction in Nighttime Photography [32.87477623401456]
  Nighttime photographers are often troubled by light pollution of unwanted artificial lights. In this paper we develop a physically-based light pollution reduction (LPR) algorithm that can substantially alleviate the degradations of perceptual quality.
  arXiv  Detail & Related papers  (2021-06-18T10:38:13Z)
• Nighttime Dehazing with a Synthetic Benchmark [147.21955799938115]
  We propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images. We generate realistic nighttime hazy images by sampling real-world light colors from a prior empirical distribution. Experiment results demonstrate their superiority over state-of-the-art methods in terms of both image quality and runtime.
  arXiv  Detail & Related papers  (2020-08-10T02:16:46Z)

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.