Learning to Enhance Visual Quality via Hyperspectral Domain Mapping

TL;DR

This paper introduces SpecNet, a deep learning architecture that leverages hyperspectral domain mapping to improve image quality, especially in low-light conditions, by estimating spectral profiles and enhancing RGB images.

Contribution

The paper presents a novel deep architecture, SpecNet, which uses hyperspectral domain mapping and unpaired cycle-consistent learning to enhance image quality beyond traditional RGB-based methods.

Findings

Effective spectral profile estimation improves low-light image enhancement.

Unpaired cycle-consistent framework generates realistic hyperspectral images.

Optimizing spectral profiles benefits real and synthetic low-light images.

Abstract

Deep learning based methods have achieved remarkable success in image restoration and enhancement, but most such methods rely on RGB input images. These methods fail to take into account the rich spectral distribution of natural images. We propose a deep architecture, SpecNet, which computes spectral profile to estimate pixel-wise dynamic range adjustment of a given image. First, we employ an unpaired cycle-consistent framework to generate hyperspectral images (HSI) from low-light input images. HSI is further used to generate a normal light image of the same scene. We incorporate a self-supervision and a spectral profile regularization network to infer a plausible HSI from an RGB image. We evaluate the benefits of optimizing the spectral profile for real and fake images in low-light conditions on the LOL Dataset.