Data relativistic uncertainty framework for low-illumination anime scenery image enhancement
This addresses the domain gap in low-light enhancement for anime scenery images, an underexplored task, but is incremental as it adapts existing ideas like Relativistic GAN to a new domain.
The study tackled low-illumination quality degradation in anime scenery images by proposing a Data Relativistic Uncertainty (DRU) framework, which dynamically adjusts objective functions to recalibrate model learning under data uncertainty, resulting in superior perceptual and aesthetic qualities beyond state-of-the-art methods.
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.