From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement

TL;DR

This paper introduces a novel zero-shot glow suppression method for nighttime images that effectively reduces glow effects and enhances visibility without requiring training data, improving over existing low-light enhancement techniques.

Contribution

It proposes a physical glow generation model and a scalable, light-aware blind deconvolution network for effective glow suppression in nighttime images, without needing training data.

Findings

Effective glow suppression demonstrated in real night scenes

Improved low-light visibility with combined glow removal and enhancement

Zero-shot learning approach eliminates the need for training data

Abstract

Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. However, these methods have limited exploration in another major visibility damage, the glow effects in real night scenes. Glow effects are inevitable in the presence of artificial light sources and cause further diffused blurring when directly enhanced. To settle this issue, we innovatively consider the glow suppression task as learning physical glow generation via multiple scattering estimation according to the Atmospheric Point Spread Function (APSF). In response to the challenges posed by uneven glow intensity and varying source shapes, an APSF-based Nighttime Imaging Model with Near-field Light Sources (NIM-NLS) is specifically derived to design a scalable Light-aware Blind Deconvolution Network (LBDN). The glow-suppressed result is then brightened via a Retinex-based Enhancement Module (REM). Remarkably, the proposed glow suppression 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.