基于物理信息集成表示的光场图像超分辨率
Physics-Informed Ensemble Representation for Light-Field Image Super-Resolution
AI总结：
本文提出利用光场成像几何先验构建虚拟狭缝图像子空间，并学习所有LF子空间的集成表示，结合几何感知解码器EPIXformer，在空间和角度超分辨率任务中优于现有方法，尤其擅长处理不同视差。
摘要：
近年来，基于学习的方法通过探索卷积或Transformer网络结构，在光场（LF）图像超分辨率（SR）方面取得了显著进展。然而，LF成像具有许多尚未被充分利用的内在物理先验。本文分析了LF成像过程的坐标变换，以揭示LF图像中的几何关系。基于这些几何先验，我们引入了一种新的虚拟狭缝图像（VSI）LF子空间，该子空间提供与子孔径图像互补的亚像素信息。为了在可控复杂度下利用四维数据中丰富的相关性，我们提出学习所有$C_4^2$个LF子空间的集成表示，以实现更有效的特征提取。为了从欠采样的LF数据中超分辨率重建图像结构，我们提出了一种几何感知解码器，名为EPIXformer，它利用LF物理先验约束Transformer的操作搜索区域。在空间和角度SR任务上的实验结果表明，所提方法优于其他最先进方案，尤其是在处理各种视差方面。
英文摘要：
Recent learning-based approaches have achieved significant progress in light field (LF) image super-resolution (SR) by exploring convolution-based or transformer-based network structures. However, LF imaging has many intrinsic physical priors that have not been fully exploited. In this paper, we analyze the coordinate transformation of the LF imaging process to reveal the geometric relationship in the LF images. Based on such geometric priors, we introduce a new LF subspace of virtual-slit images (VSI) that provide sub-pixel information complementary to sub-aperture images. To leverage the abundant correlation across the four-dimensional data with manageable complexity, we propose learning ensemble representation of all $C_4^2$ LF subspaces for more effective feature extraction. To super-resolve image structures from undersampled LF data, we propose a geometry-aware decoder, named EPIXformer, which constrains the transformer's operational searching regions with a LF physical prior. Experimental results on both spatial and angular SR tasks demonstrate that the proposed method outperforms other state-of-the-art schemes, especially in handling various disparities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
