Data relativistic uncertainty framework for low-illumination anime scenery image enhancement

TL;DR

This paper introduces a novel Data Relativistic Uncertainty framework for low-illumination anime scenery image enhancement, addressing domain gaps and data scarcity by leveraging uncertainty information to improve perceptual quality.

Contribution

It proposes a new uncertainty-based framework inspired by Relativistic GANs, specifically designed for anime scenery enhancement under diverse illumination conditions.

Findings

Outperforms state-of-the-art methods in perceptual quality

Effectively handles data uncertainty in low-light anime images

Demonstrates versatility across different versions of EnlightenGANs

Abstract

By contrast with the prevailing works of low-light enhancement in natural images and videos, this study copes with the low-illumination quality degradation in anime scenery images to bridge the domain gap. For such an underexplored enhancement task, we first curate images from various sources and construct an unpaired anime scenery dataset with diverse environments and illumination conditions to address the data scarcity. To exploit the power of uncertainty information inherent with the diverse illumination conditions, we propose a Data Relativistic Uncertainty (DRU) framework, motivated by the idea from Relativistic GAN. By analogy with the wave-particle duality of light, our framework interpretably defines and quantifies the illumination uncertainty of dark/bright samples, which is leveraged to dynamically adjust the objective functions to recalibrate the model learning under data uncertainty. Extensive experiments demonstrate the effectiveness of DRU framework by training several versions of EnlightenGANs, yielding superior perceptual and aesthetic qualities beyond the state-of-the-art methods that are incapable of learning from data uncertainty perspective. We hope our framework can expose a novel paradigm of data-centric learning for potential visual and language domains. Code is available.