论文标题
学习纹理变压器网络用于光场超级分辨率
Learning Texture Transformer Network for Light Field Super-Resolution
论文作者
论文摘要
由于固有的空间 - 角折衷方案，手持式光场摄像机的空间分辨率低。在本文中，我们提出了一种借助纹理变压器网络（TTSR）来改善光场图像空间分辨率的方法。所提出的方法由三个模块组成：第一个模块产生一个全in焦点高分辨率透视图像，该图像用作第二个模块的参考图像，即TTSR，从而产生高分辨率的光场。最后一个模块通过先验施加光场来完善空间分辨率。结果表明，在双尺化大小的光场图像上大约4 dB至6 dB PSNR增益
Hand-held light field cameras suffer from low spatial resolution due to the inherent spatio-angular tradeoff. In this paper, we propose a method to improve the spatial resolution of light field images with the aid of the Texture Transformer Network (TTSR). The proposed method consists of three modules: the first module produces an all-in focus high-resolution perspective image which serves as a reference image for the second module, i.e. TTSR, which in turn produces a high-resolution light field. The last module refines the spatial resolution by imposing a light field prior. The results demonstrate around 4 dB to 6 dB PSNR gain over a bicubically resized light field image
