View Interpolation Networks for Reproducing Material Appearance of Specular Objects
View Interpolation Networks for Reproducing Material Appearance of Specular Objects
复制标题
DOI：
10.1016/j.vrih.2022.11.001
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Chihiro Hoshizawa;T. Komuro
中科院分区：
文献类型：
--
作者：
Chihiro Hoshizawa;T. Komuro
背景在这项研究中，我们提出了视点内插网络来重现对象表面亮度随观察方向的变化，这对于重现真实对象的材质外观是很重要的。这些网络被训练成从放置在正方形角落的四个摄像头的中间视点生成图像。实验采用三种不同的方法组合和训练数据格式。结果我们确定，将视点的坐标和四个摄像头图像一起输入，并使用随机视点的图像作为训练数据，效果最好。
BackgroundIn this study, we propose view interpolation networks to reproduce changes in the brightness of an object′s surface depending on the viewing direction, which is important for reproducing the material appearance of a real object.MethodWe used an original and modified version of U-Net for image transformation. The networks were trained to generate images from the intermediate viewpoints of four cameras placed at the corners of a square. We conducted an experiment using with three different combinations of methods and training data formats.ResultWe determined that inputting the coordinates of the viewpoints together with the four camera images and using images from random viewpoints as the training data produces the best results.