基于球面几何增强的全景图像边缘聚焦超分辨率
Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation
针对全景图像超分辨率中的边缘退化问题，提出边缘聚焦模块与球面旋转-平移数据增强策略，可复用于其他畸变图像复原任务。
原文依据 Omnidirectional image super-resolution (ODISR) remains challenging due to extreme magnification factors (e.g., 8x, 16x) and projection-specific distortions, which degrade edge integrity and limit model performance.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全景图像超分辨率（ODISR）由于极高的放大倍数（例如8倍、16倍）和投影特定的畸变而仍然具有挑战性，这些因素会降低边缘完整性并限制模型性能。本文提出了一种结合球面几何增强的边缘聚焦框架来解决这些问题。我们的方法包括一个边缘聚焦模块（EFB），它通过边缘增强和细化模块整合空间-通道注意力，加强边缘特征捕获和优化。我们还设计了一个边缘感知多尺度（EAM）流程，利用浅层卷积进行初始特征提取，局部模块进行深度挖掘，以及全局整合模块进行多尺度聚合，确保畸变区域中连贯的边缘重建。为了缓解数据稀缺，我们引入了一种基于球面投影的旋转-平移增强策略，在保持场景连续性的同时扩展数据集。大量实验表明，我们的方法在公开数据集上优于最优方法。
英文原文摘要 1056 字符
Omnidirectional image super-resolution (ODISR) remains challenging due to extreme magnification factors (e.g., 8x, 16x) and projection-specific distortions, which degrade edge integrity and limit model performance. This paper proposes an edge-focused framework combined with spherical geometric augmentation to address these issues. Our approach includes an Edge Focused Block (EFB) that integrates spatial-channel attention via Edge Enhanced and Refined Blocks, strengthening edge feature capture and optimization. We also design an Edge-Aware Multi-Scale (EAM) pipeline, leveraging shallow convolutions for initial feature extraction, local modules for deep mining, and a Global Integration Block for multi-scale aggregation, ensuring coherent edge reconstruction in distorted regions. To mitigate data scarcity, we introduce a rotation-translation augmentation strategy based on spherical projections, expanding datasets while preserving scene continuity. Extensive experiments show our method outperforms state-of-the-art approaches on public datasets.