arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08819cs.CVcs.GRcs.NE
收藏

光照模型对合成训练数据集生成影响的研究

A study of the effect of the illumination model on the generation of synthetic training datasets

Durham University(杜伦大学)

Xin Zhang, Ning Jia, Ioannis Ivrissimtzis

摘要:

当真实图像稀缺或昂贵时,使用计算机生成的图像来训练深度神经网络是真实图像的可行替代方案。在本文中,我们研究了渲染软件所使用的照明模型如何影响生成的图像的质量。我们创建了八个训练集,每个训练集都有不同的照明模型,并在三种不同的网络架构上进行测试,ResNet,U-Net和我们开发的组合架构。测试集由3D打印物体的照片组成,这些照片是从用于生成训练集的相同CAD模型中生成的。渲染过程的其他参数(如纹理和相机位置)的效果是随机的。我们的研究结果表明,照明模型的效果是重要的,可比的意义上的网络架构。我们还表明,这两个光探头捕捉自然环境光,和模拟照明环境,可以得到很好的结果。在光探头的情况下,我们确定为两个重要的因素影响性能的光探头和测试环境之间的相似性,以及光探头的分辨率。关于模拟的照明环境,与测试环境的相似性再次被确定为重要因素。

英文摘要:

The use of computer generated images to train Deep Neural Networks is a viable alternative to real images when the latter are scarce or expensive. In this paper, we study how the illumination model used by the rendering software affects the quality of the generated images. We created eight training sets, each one with a different illumination model, and tested them on three different network architectures, ResNet, U-Net and a combined architecture developed by us. The test set consisted of photos of 3D printed objects produced from the same CAD models used to generate the training set. The effect of the other parameters of the rendering process, such as textures and camera position, was randomized. Our results show that the effect of the illumination model is important, comparable in significance to the network architecture. We also show that both light probes capturing natural environmental light, and modelled lighting environments, can give good results. In the case of light probes, we identified as two significant factors affecting performance the similarity between the light probe and the test environment, as well as the light probe's resolution. Regarding modelled lighting environment, similarity with the test environment was again identified as a significant factor.

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。

↑