针对动漫场景暗光图像，提出基于数据不确定性的增强框架。
Data relativistic uncertainty framework for low-illumination anime scenery image enhancement
- 借鉴相对论GAN思想，定义光照不确定性并动态调整损失函数。
- 在自建动漫场景数据集上显著提升图像感知与美学质量。
- 适合关注数据不确定性与图像增强的科研与工程人员。
与自然图像和视频的低光照增强研究不同，本文聚焦动漫场景图像在低光照下的质量退化问题，以弥合领域差距。由于该任务尚未被充分探索，我们从多个来源收集图像，构建了一个包含多种环境与光照条件的非配对动漫场景数据集，缓解数据稀缺问题。为利用多样光照条件下隐含的不确定性信息，提出数据相对论不确定性（DRU）框架，受相对论GAN启发，类比光的波粒二象性，可解释性地定义并量化明暗样本的光照不确定性，进而动态调整目标函数，重新校准模型在数据不确定性下的学习过程。大量实验表明，基于DRU框架训练的EnlightenGAN变体，在视觉感知与美学质量上均优于现有方法，且后者无法从数据不确定性视角学习。本工作希望为视觉与语言等领域的数据驱动学习提供新范式。代码已公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。