Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited detector resolution has to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable part of the LF camera processing pipeline. The high-dimensionality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. The performance of existing methods is still limited as they fail to thoroughly explore the coherence among LF sub-aperture images (SAIs) and are insufficient in accurately preserving the scene's parallax structure. To tackle this challenge, we propose a novel learning-based LF spatial SR framework. Specifically, each SAI of an LF image is first coarsely and individually super-resolved by exploring the complementary information among SAIs with selective combinatorial geometry embedding. To achieve efficient and effective selection of the complementary information, we propose two novel sub-modules conducted hierarchically: the patch selector provides an option of retrieving similar image patches based on offline disparity estimation to handle large-disparity correlations; and the SAI selector adaptively and flexibly selects the most informative SAIs to improve the embedding efficiency. To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation. In addition, we extend the proposed method to irregular LF data. To the best of our knowledge, this is the first learning-based SR method for irregular LF data. Experimental results over both synthetic and real-world LF datasets demonstrate the significant advantage of our approach over state-of-the-art methods.
翻译:手持装置所获取的浅光场图像通常具有低空间分辨率,因为有限的探测器分辨率必须与角尺寸共享。 因此,LF空间超分辨率(SR)成为LF摄像处理管道中不可或缺的部分。 LF图像的高维特征和复杂的几何结构使得问题比传统的单一图像SR更具挑战性。 现有方法的性能仍然有限,因为它们未能彻底探索LF子孔图(SAI)的一致性,并且不足以准确保存场景的螺旋结构。 为了应对这一挑战,我们提议建立一个基于学习的LF空间超分辨率(SR)框架。具体地说,一个LF图像的每个SAI首先粗略和个别地解析,通过探索具有选择性组合式几处图像嵌入嵌入的SAI的辅助信息。为了实现高效和有效选择补充信息,我们提议了两个新型的子模块: 补差选择了我们基于离线估计的图像补差的首选方案, 以基于离线的LFS-LS-L 空间空间SR框架框架框架框架框架为新的学习基础, 选择了我们经过最不易变现的智能的SAL- real- real- realal- real- real- realal-al-al- redudududeal- dalationalational- dationaldal-ladingaldaldaldal- disldaldaldaldaldaldaldaldaldaldaldal) 和S