论文标题
MINL：基于微图像的光场神经表示
MiNL: Micro-images based Neural Representation for Light Fields
论文作者
论文摘要
光场的传统表示形式可以分为两种类型：显式表示和隐式表示。与将光场表示为基于子孔的图像（SAI）阵列或微图像（MIS）透镜图像的明确表示不同，隐式表示将光场视为神经网络，这与离散的显式表示相反，这是固有的连续表示。但是，目前，光场的几乎所有隐式表示都利用SAI来训练MLP，以学习从4D空间角坐标到像素颜色的像素映射，这既不紧凑，也不是较低的复杂性。取而代之的是，在本文中，我们提出了Minl，这是一种新型的MI-Wise隐式神经表示，用于训练MLP + CNN，以学习从2D MI坐标到MI颜色的映射。考虑到微图像的坐标，MINL输出相应的微图像的RGB值。 MINL中编码的光场只是训练一个神经网络以回归微图像，而解码过程是一个简单的前馈操作。与普通像素的隐式表示相比，MINL更加紧凑，更高效，具有更快的解码速度（\ textbf {$ \ times $ 80 $ \ sim $ 180}加速）以及更好的视觉质量（\ textbf {1 $ \ sim $ 4DB} psnr平均改善）。
Traditional representations for light fields can be separated into two types: explicit representation and implicit representation. Unlike explicit representation that represents light fields as Sub-Aperture Images (SAIs) based arrays or Micro-Images (MIs) based lenslet images, implicit representation treats light fields as neural networks, which is inherently a continuous representation in contrast to discrete explicit representation. However, at present almost all the implicit representations for light fields utilize SAIs to train an MLP to learn a pixel-wise mapping from 4D spatial-angular coordinate to pixel colors, which is neither compact nor of low complexity. Instead, in this paper we propose MiNL, a novel MI-wise implicit neural representation for light fields that train an MLP + CNN to learn a mapping from 2D MI coordinates to MI colors. Given the micro-image's coordinate, MiNL outputs the corresponding micro-image's RGB values. Light field encoding in MiNL is just training a neural network to regress the micro-images and the decoding process is a simple feedforward operation. Compared with common pixel-wise implicit representation, MiNL is more compact and efficient that has faster decoding speed (\textbf{$\times$80$\sim$180} speed-up) as well as better visual quality (\textbf{1$\sim$4dB} PSNR improvement on average).
