LapEPI-Net：一种用于基于学习的密集光场重建的拉普拉斯金字塔EPI结构
LapEPI-Net: A Laplacian Pyramid EPI structure for Learning-based Dense Light Field Reconstruction
摘要：
对于密集采样光场（LF）重建问题，现有的方法集中在一个无深度的框架，以实现非朗伯性能。然而，它们陷入了“混叠或模糊”问题的权衡，即，对混叠分量（由输入LF的角度稀疏性引起）进行预滤波总是导致模糊的结果。在本文中，我们打算通过在基于学习的框架内引入精心设计的对极平面图像（EPI）结构来解决这一挑战。具体来说，我们首先分析表明，减少EPI的空间尺度显示更高的效率，在解决混叠问题比简单地采用预滤波。因此，我们设计了一个拉普拉斯金字塔EPI（LapEPI）结构，其中包含低空间尺度EPI（用于混叠）和高频残差（用于模糊），以解决权衡问题。然后，我们提出了一种新的网络架构的LapEPI结构，称为LapEPI网。为了确保非朗伯性能，我们采用了迁移学习策略，首先用自然图像预训练网络，然后用非结构化LF对其进行微调。大量的实验表明，所提出的方法的高性能和鲁棒性，以解决混淆或模糊的问题，以及非朗伯重建。
英文摘要：
For dense sampled light field (LF) reconstruction problem, existing approaches focus on a depth-free framework to achieve non-Lambertian performance. However, they trap in the trade-off "either aliasing or blurring" problem, i.e., pre-filtering the aliasing components (caused by the angular sparsity of the input LF) always leads to a blurry result. In this paper, we intend to solve this challenge by introducing an elaborately designed epipolar plane image (EPI) structure within a learning-based framework. Specifically, we start by analytically showing that decreasing the spatial scale of an EPI shows higher efficiency in addressing the aliasing problem than simply adopting pre-filtering. Accordingly, we design a Laplacian Pyramid EPI (LapEPI) structure that contains both low spatial scale EPI (for aliasing) and high-frequency residuals (for blurring) to solve the trade-off problem. We then propose a novel network architecture for the LapEPI structure, termed as LapEPI-net. To ensure the non-Lambertian performance, we adopt a transfer-learning strategy by first pre-training the network with natural images then fine-tuning it with unstructured LFs. Extensive experiments demonstrate the high performance and robustness of the proposed approach for tackling the aliasing-or-blurring problem as well as the non-Lambertian reconstruction.
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。
