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

2025-12-26

AI Summary

This work addresses the underexplored problem of low-light enhancement for anime-style images. We introduce the first unpaired, multi-source anime landscape dataset and propose the Data Relative Uncertainty (DRU) framework—the first to incorporate “relativity” into low-light enhancement by dynamically calibrating illumination estimation through modeling illumination uncertainty between bright and dark samples. DRU integrates relativistic GAN-inspired uncertainty modeling, adaptive weighted loss, and an unpaired image translation mechanism, enabling end-to-end optimization driven by data uncertainty. Extensive experiments on multiple anime test sets demonstrate significant improvements over state-of-the-art methods, with enhanced perceptual quality, aesthetic naturalness, and fine-grained detail preservation. The code is publicly available.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Computer Vision: Diffusion Models for Vision

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Enhances low-illumination anime scenery images
• Addresses data scarcity with a curated unpaired dataset
• Proposes a framework to leverage illumination uncertainty

Innovation

• Constructs unpaired anime scenery dataset for data scarcity
• Proposes Data Relativistic Uncertainty framework for illumination uncertainty
• Dynamically adjusts objective functions to recalibrate model learning