基于参考图像的原子模型渲染方法  

Atomic model rendering method based on reference images

作　　者：吴晨 曹力[1] 秦宇 吴苗苗 顾兆光 WU Chen;CAO Li;QIN Yu;WU Miao-miao;Koo SiuKong(School of Computer and Information,Hefei University of Technology,Hefei Anhui 230601,China;Hong Kong Quantum AI Lab,Hong Kong 999077,China)

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230601 [2]香港量子人工智能实验室有限公司,中国香港999077

出　　处：《图学学报》2022年第6期1080-1087,共8页Journal of Graphics

基　　金：国家自然科学基金项目(61602146)。

摘　　要：伴随着生物学的发展与纳米电子器件仿真技术的进步,原子结构在现代化科技领域发挥至关重要的作用。原子结构的复杂细节使得渲染效果受光源位置影响较大,导致了原子模型渲染工作的困难。基于此,提出了一种基于参考图像的原子模型渲染方法,计算出参考图像的光照参数用于原子模型的渲染。首先,通过改变光源位置,利用POV-Ray脚本实现不同光源角度下的批量模型渲染,采集光源位置参数及渲染图像得到对应光源位置的渲染图像数据集;接着,以残差神经网络为主干设计光源估计网络,并在网络中嵌入注意力机制提升网络准确性,使用优化后的光源估计网络对数据集进行训练,回归光源位置参数;最后将训练好的卷积神经网络应用于参考图像的渲染参数估计中,利用渲染参数渲染目标模型。实验结果显示。通过网络预测的参数与真实照明参数误差极小,具有高度可靠性。Along with advances in biology and the simulation of nano electronic devices,atomic structures play a crucial role in modern science and technology.The complex details of the atomic structure result in the far-reaching impact of the position of the light source on the rendering effect,incurring difficulties in rendering atomic models.On this basis,an atomic model rendering method based on a reference image was proposed,in which the lighting parameters of the reference image were calculated for the rendering of the atomic model.First,a POV-Ray script was used to render a batch of models at different light angles by changing the light source positions,and the light source position parameters and rendered images were collected to obtain a dataset of rendered images corresponding to the light source positions.Then,the light source estimation network was designed with the residual neural network as the backbone,and the attention mechanism was embedded in the network to enhance the network accuracy.The optimized light source estimation network was employed to train the dataset and regress the light source location parameters.Finally,the trained convolutional neural network was used to estimate the rendering parameters of the reference image,and the target model was rendered using the rendering parameters.The experimental results show that the parameters predicted by the network are highly reliable with minimal error compared with the real lighting parameters.

关 键 词：原子结构 模型渲染 光源位置 参考图像 光源估计网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]