论文标题
$ \ ell_ \ infty $编码光场图像的深度解码图像
Deep Decoding of $\ell_\infty$-coded Light Field Images
论文作者
论文摘要
为了丰富传统摄像机的功能，光场摄像头记录了光线的强度和方向，因此可以通过计算用用户定义的摄像头参数呈现图像。增加的功能和灵活性是以收集通常超过$ 100 \ tims $ $ $ $ $ $的信息来获得的。为了应对此问题，已经引入了几种光场压缩方案。但是，它们利用多维光场数据相关性的方式很复杂，因此不适合廉价的光场摄像机。在这项工作中，我们提出了一种新颖的$ \ ell_ \ infty $限制的光场图像压缩系统，该系统具有非常低的复杂性DPCM编码器和一个基于CNN的深层解码器。 CNN解码器靶向高保真重建，将资本利用在$ \ ell_ \ infty $ -constraint和Light Field属性上，以删除压缩伪像，并且比现有的现有最新的$ \ ell_2 $ blate _2 $ - 基于基于基于的$ \ ell_2 $ - 基于基于的光场压缩方法。
To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations. The added capability and flexibility are gained at the cost of gathering typically more than $100\times$ greater amount of information than conventional images. To cope with this issue, several light field compression schemes have been introduced. However, their ways of exploiting correlations of multidimensional light field data are complex and are hence not suited for inexpensive light field cameras. In this work, we propose a novel $\ell_\infty$-constrained light-field image compression system that has a very low-complexity DPCM encoder and a CNN-based deep decoder. Targeting high-fidelity reconstruction, the CNN decoder capitalizes on the $\ell_\infty$-constraint and light field properties to remove the compression artifacts and achieves significantly better performance than existing state-of-the-art $\ell_2$-based light field compression methods.
