利用图像对称性实现无监督去雾，无需真实清晰图像
Equivariant Learning for Unsupervised Image Dehazing
- 基于图像信号对称性设计无监督学习框架
- 在细胞显微和内窥镜等科学图像上显著优于现有方法
- 适合缺乏清晰样本的科研成像场景
图像去雾（ID）旨在从被雾霾污染的观测图像中恢复清晰图像。当前方法通常依赖精心设计的先验或大量无雾真值数据，这些在科学成像中获取成本高且不切实际。本文提出一种新的无监督学习框架——等变图像去雾（EID），通过利用图像信号的对称性，直接从原始模糊图像中恢复清晰结构。通过强制雾霾一致性与系统等变性，EID可有效重建清晰模式。此外，提出对抗学习策略以建模未知的雾霾物理特性，促进EID学习。在两个科学图像去雾基准（包括细胞显微和医学内窥镜）及自然图像去雾上的实验表明，EID显著优于现有先进方法。通过将等变学习与雾霾物理建模相结合，期望为科学成像提供更通用、高效的去雾解决方案。代码与数据集将公开。
原文摘要 · Abstract (English)
Image Dehazing (ID) aims to produce a clear image from an observation contaminated by haze. Current ID methods typically rely on carefully crafted priors or extensive haze-free ground truth, both of which are expensive or impractical to acquire, particularly in the context of scientific imaging. We propose a new unsupervised learning framework called Equivariant Image Dehazing (EID) that exploits the symmetry of image signals to restore clarity to hazy observations. By enforcing haze consistency and systematic equivariance, EID can recover clear patterns directly from raw, hazy images. Additionally, we propose an adversarial learning strategy to model unknown haze physics and facilitate EID learning. Experiments on two scientific image dehazing benchmarks (including cell microscopy and medical endoscopy) and on natural image dehazing have demonstrated that EID significantly outperforms state-of-the-art approaches. By unifying equivariant learning with modelling haze physics, we hope that EID will enable more versatile and effective haze removal in scientific imaging. Code and datasets will be published.
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。