通过自适应归一化与特征提升，解决高动态范围成像中的饱和模糊问题。
Scale Equivariance Regularization and Feature Lifting in High Dynamic Range Modulo Imaging
- 引入尺度等变正则化，保持曝光变化下的重建一致性
- 融合原始模图像、包裹差分与闭式初始化，提升特征表达能力
- 在感知与线性指标上达到当前最优，适合图像恢复研究者
模成像通过循环包裹饱和强度实现高动态范围（HDR）采集，但自然图像边缘与人工环绕断点之间的模糊性导致重建困难。本文提出一种基于学习的HDR重建框架，包含两项关键技术：(i) 尺度等变正则化，强制在曝光变化下保持一致性；(ii) 特征提升输入设计，结合原始模图像、包裹有限差分和闭式初始化。二者协同增强网络区分真实结构与环绕伪影的能力，在感知与线性HDR质量指标上均取得当前最优表现。
原文摘要 · Abstract (English)
Modulo imaging enables high dynamic range (HDR) acquisition by cyclically wrapping saturated intensities, but accurate reconstruction remains challenging due to ambiguities between natural image edges and artificial wrap discontinuities. This work proposes a learning-based HDR restoration framework that incorporates two key strategies: (i) a scale-equivariant regularization that enforces consistency under exposure variations, and (ii) a feature lifting input design combining the raw modulo image, wrapped finite differences, and a closed-form initialization. Together, these components enhance the network's ability to distinguish true structure from wrapping artifacts, yielding state-of-the-art performance across perceptual and linear HDR quality metrics.
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。