反射剖面精确拟合的次表面散射计算方法

近年来,随着电影、游戏、虚拟现实应用等对真实感要求的不断提高,针对人体组织、牛奶等半透明材质的实时渲染变得越发重要.针对当前大部分次表面散射计算方法难以正确估计散射范围的问题,提出了一种全新的次表面散射计算方法用以精确表示最大散射距离.首先,针对暴力蒙特卡洛光子追踪结果进行模拟,以得到反射剖面结果.其次通过多项式模型进行反射剖面拟合,计算精确着色点处的最大散射范围.最后,提出了一种新的重要性采样方案以减少蒙特卡洛所需的采样数,进一步提高计算效率.此外,方法所需的参数仅由着色点上的反射率以及材质平均自由程提供,以便于灵活调整渲染效果.实验证明,所提模型避免了之前对于散射范围的错误估计,对材质反射率复杂的区域具有更好的渲染精度,且渲染速率满足实时要求.     

一种径向基函数神经网络的参数求解方法

为了求解径向基函数神经网络的权值,首先分析了传统基于训练误差的方法,发现该方法容易造成数据过拟合,原因在于训练误差是风险函数的下偏估计;因此,文中提出采用缺一交叉验证得分代替训练误差,来实现无偏估计风险函数;实验对摩托数据与玻璃数据进行拟合,证实了基于缺一交叉验证的方法优于传统基于训练误差的方法,且所得到的径向基函数网络能够较光滑地拟合数据,不会造成过拟合.     

虚拟数字人实时卡通渲染研究

为了渲染虚拟数字人体各部位材质的特性,增加虚拟数字人仿真渲染的艺术表现力,提出了结合卡通渲染艺术表现力与仿真渲染材质特性的渲染方法。使用改进的Kajiya光照模型实现具有卡通风格和物理特性的头发渲染,利用有向距离场技术制作面部阴影贴图控制面部阴影的卡通化形状,运用视差贴图技术和材质捕获技术模拟眼球的折射和反射现象,使用色调映射技术模拟皮肤的次表面散射、散射光漫反射和皮肤的边缘透光效果,实现虚拟数字人重点部位的实时卡通渲染。实验结果表明,结合仿真渲染材质特性的卡通渲染方法能够实现虚拟数字人的实时渲染,同时能够兼顾材质真实特性与艺术效果。     

基于L-MBP算法对RoboCup仿真训练工具的设计

采用L-M BP算法fLevenbergMarquardt BP算法),设计了神经网络训练测试工具,对阵形、防守位置敏感度、进攻位置敏感度和射门都采用了神经网络来进行数据拟合.利用神经网络存储离线采集的数据,实现未训练到的数据的正确输出.     

一种新的神经网络逼近函数算法

针对地震数据等大数据多属性集处理一直是科学研究的重点和难点,本文提出一种多参数的单调性函数的拟合方法。利用主成分分析法来进行简化处理,从而获得较少的属性集合,并在此基础上,提出一种新的数据预处理方法,以较好地解决数据单调性所带来的归一化误差,并构造一个与之相匹配的神经网络模型,用它的学习算法来训练网络,从而实现函数拟合。最后通过仿真验证了该方法的有效性。     

基于支持向量机的缺失数据补齐方法

根据SVM在函数拟合方面的特点,建立了一个函数模型。通过确定主要影响因子和选定数据集后,对该模型进行了训练,最后成功地应用于缺失数据补齐。经过真实工程数据实验证实,基于SVM的缺失数据补齐方法具有明显实用性。     

基于自适应神经模糊系统的足球机器人射门点的确定

针对足球机器人射门行为中运算的高复杂性和反应延迟的局限,引入一种基于类高斯函数的自适应神经模糊推理系统（ANFIS）,用于确定最合适的射门点.系统由前件网络和后件网络构成,结合模糊逻辑理论,建立基于人类语言描述的射门行为模型.采用实际的比赛记录作为训练数据,离线地拟合系统输入与输出之间的映射关系,经训练的系统能够自动地调整前期隶属度函数的形状和后期的自适应权值.仿真结果表明,射门成功率和反应速度都能够达到预期的效果,方法的有效性得到了验证.     

应用薄膜干涉模型进行蝴蝶彩色效果物理绘制

针对当前蝴蝶彩色效果绘制方法的真实感问题,提出一种应用薄膜干涉模型的真实感绘制方法.首先根据蝴蝶表面脊突结构构造多层薄膜模型;然后利用多层薄膜干涉原理模拟光在薄膜内部的多次反射、透射形成的混合散射特性,其中,菲涅尔公式被引入以解释反射或透射波的幅值变化,微表面散射因子被创造性地引入来模拟蝴蝶粗糙表面的各向异性特性;最后通过全波长光谱建模增强干涉效果,在此基础上还将该算法与光线追踪渲染框架相结合,构建了可应用于光线追踪器的波动双向散射分布函数干涉模型,以精确地模拟光的幅值和相位变动.实验结果表明,该模型能够有效地绘制出较为逼真的蝴蝶彩色效果.     

重加权在多类别不平衡医学图像检测中的应用

在医学图像检测中,由于数据集经常存在每类样本数目不均衡的情况,使数据集样本出现长尾分布的问题,严重影检测模型的性能。针对网络在训练多类别不均衡数据集中训练时出现的过拟合现象,采用重加权的方式改进原有损失函数,并用CLAHE算法对X光图像进行预处理,以突出图像的内部细节,选用ResNext50网络作为特征提取网络。以covid-chestxray数据集作为实验用数据集,通过实验评估了模型的准确度、精确率、召回率和F1值,证实了该方法的有效性。     

基于集成降噪自编码的在线网络入侵检测模型

针对神经网络在线入侵检测模型训练时易出现过拟合和泛化能力弱的问题,提出基于改进的集成降噪自编码在线入侵检测模型以区分正常和异常的流量模式。降噪自编码减少了训练数据与测试数据的差别,缓解过拟合问题,提高模型的性能。同时阈值的选择方法直接影响网络入侵检测模型检测精度,该阈值采用随机方法确定,无须于离线入侵检测,不需通过完整的数据集即可选择最佳的阈值。采用CICIDS2017中的异常的数据流对模型进行测试,准确率分别为90.19%。结果表明,作为一种在线检测模型,提出的异常检测模型优于其他异常检测方法。     

MesoGAN: Generative Neural Reflectance Shells

We introduce MesoGAN, a model for generative 3D neural textures. This new graphics primitive represents mesoscale appearance by combining the strengths of generative adversarial networks (StyleGAN) and volumetric neural field rendering. The primitive can be applied to surfaces as a neural reflectance shell; a thin volumetric layer above the surface with appearance parameters defined by a neural network. To construct the neural shell, we first generate a 2D feature texture using StyleGAN with carefully randomized Fourier features to support arbitrarily sized textures without repeating artefacts. We augment the 2D feature texture with a learned height feature, which aids the neural field renderer in producing volumetric parameters from the 2D texture. To facilitate filtering, and to enable end-to-end training within memory constraints of current hardware, we utilize a hierarchical texturing approach and train our model on multi-scale synthetic datasets of 3D mesoscale structures. We propose one possible approach for conditioning MesoGAN on artistic parameters (e.g. fibre length, density of strands, lighting direction) and demonstrate and discuss integration into physically based renderers.     

可微绘制技术研究进展

可微绘制技术是当前虚拟现实、计算机图形学与计算机视觉领域研究的热点,其目标是改造计算机图形学中以光栅化或光线跟踪算法为主的真实感绘制流程,支持梯度信息回传以计算由输出图像的变化导致的输入几何、材质属性变化,通过与优化及深度学习技术等相结合支持从数据中学习绘制模型和逆向推理,是可微学习技术在计算机图形学绘制技术中的应用的具体体现,在增强/虚拟现实内容生成、三维重建、表观采集建模和逆向光学设计等领域中有广泛的应用前景。本文对可微绘制当前的发展状况进行调研,重点对该技术在真实感绘制、3维重建和表观采集建模中的研究和应用情况进行综述,并对可微绘制技术发展趋势进行展望,以期推动可微技术在学术界和产业界的进一步发展。     

Physically Based Real-Time Rendering of Teeth and Partial Restorations

Visually accurate real-time rendering of teeth has many applications ranging from computer games to dental computer aided design (CAD). Similar to skin, the realistic and physically correct appearance of teeth cannot be achieved by simply using opaque diffuse textures, mainly because of the subsurface scattering behaviours of both. While both have a layered structure in common, the scattering characteristics of the teeth layers are drastically different from those of the skin, making rendering much more complicated. We present an approach which uses the Henyey–Greenstein scattering to achieve a near realistic real-time rendering of human teeth. To simulate the multi-layered geometry of teeth, we use standardized teeth models with dentin cores and fit them to real scanned teeth or dental restorations. By using a proxy geometry to compute the scattering, we can also render partial restorations as they would look like when attached to the remaining teeth. Finally, we compare our results to the VITA shade systems and human teeth to evaluate the visual fidelity of our approach.     

Neuro-controller for broadcast lighting light-emitting diode to express white light with high color rendering index

Technical characteristics analysis related to correlated color temperature (CCT), color rendering, and illuminance is required to use light-emitting diode (LED) as broadcast lighting. In general, to realize a white light source with a high color rendering index (CRI), we selected the appropriate emission intensity of RGBW LED through trial and error. However, the characteristics of the LED light source and environmental conditions make it difficult to perform the procedure several times. The objective of this study was to design a system that could control illuminance, CCT, and ∆uv while having high CRI, as an LED control method for broadcasting lighting. The controller implements using a feed-forward neural network with excellent nonlinear function approximation capability. We measure data directly from the red green blue white (RGBW) LED system for neural network training. We then select data with high CRI from the measured raw data and choose data for neural network learning by removing measurement noise using the quadratic polynomial interpolation method. The performance evaluation confirms that the proposed neural network controller shows excellent results as an RGBW LED controller for broadcast lighting in the Planckian locus and all regions of white light.     

应用RBF神经网络的体绘制传递函数设计方法

提出一种基于RBF神经网络的体绘制多维传递函数设计方法,利用直观的交互界面,通过画笔获得感兴趣体素的特征信息作为训练样本对RBF神经网络进行训练,使用训练后的RBF神经网络实现全部体素的分类识别,对不同的分类结果赋予不同的光学参数进行显示,自动完成传递函数的设计。实验结果表明,所设计的交互界面能直观方便地定义感兴趣的对象,大幅提高人机交互的效率;RBF神经网络的自主学习能力能够避免传递函数设计的盲目性,增强感兴趣区域的绘制效果,实现传递函数设计的自动化和智能化。     

Rendering of Surface and Volume Details in Volume Data*

Aiming at the detail rendering in volume data, a new volume illumination model, called Composed Scattering Model (CSM), is presented. In order to enhance different details in volume data, scattering intensity is decomposed into volume scattering intensity and surface scattering intensity with different weight functions. According to the Gauss probability distribution of gray and gradient of data, we propose an accurate method to detect the materials in a voxel, called composed segmentation. In addition, we discuss the principle of constructing these weight functions based on the operators defined in composed segmentation. CSM can generate images containing more details than most popular volume rendering models. This model has been applied to the direct volume rendering of 3D data sets obtained by CT and MRI. The resultant images show not only rich details but also clear boundary surfaces. CSM is demonstrated as an accurate volume rendering model suited for detail enhancement in volume data sets.     

Composed Scattering Model for Direct Volume Rendering

Based on the equation of transfer in transport theory of optical physics,a new volume rendering model,called composed scattering model(CSM),is presented.In calculating the scattering term of the equation,it is decomposed into volume scattering intensity and surface scattering intensity,and they are composed with the boundary detection operator as the weight function.This proposed model differs from the most current volume rendering models in the aspect that in CSM segmentation and illumination intensity calculation are taken as two coherent parts while in existing models they are regarded as two separate ones.This model has been applied to the direct volume rendering of 3D data sets obtained by CT and MRI.The resultant images show not only rich details but also clear boundary surfaces.CSM is demonstrated to be an accurate volume rendering model suitable for CT and MRI data sets.     

Interactive Subsurface Scattering for Materials With High Scattering Distances

Existing algorithms for rendering subsurface scattering in real time cannot deal well with scattering over longer distances. Kernels for image space algorithms become very large in these circumstances and separation does not work anymore, while geometry-based algorithms cannot preserve details very well. We present a novel approach that deals with all these downsides. While for lower scattering distances, the advantages of geometry-based methods are small, this is not the case anymore for high scattering distances (as we will show). Our proposed method takes advantage of the highly detailed results of image space algorithms and combines it with a geometry-based method to add the essential scattering from sources not included in image space. Our algorithm does not require pre-computation based on the scene's geometry, it can be applied to static and animated objects directly. Our method is able to provide results that come close to ray-traced images which we will show in direct comparisons with images generated by PBRT. We will compare our results to state of the art techniques that are applicable in these scenarios and will show that we provide superior image quality while maintaining interactive rendering times.      

基于区域行性解释的表达型绘制

文中主要研究了CAD领域中的表达型绘制技术,针对机械零件的转折润饰的特点,提出了以表面特性解释为基础的表达型绘制方法,进而系统地研究了基于区域特性来模拟不同表面润饰的各种手法和关键算法,并完成了一个实验系统RETOUCH。     

Subsurface scattering using splat-based diffusion in point-based rendering

Point-based graphics has gained much attention as an alternative to polygon-based approaches because of its simplicity and flexibility. However, current point-based techniques do not provide a sufficient rendering quality for translucent materials such as human skin. In this paper, we propose a point-based framework with subsurface scattering of light, which is important to create the soft and semi-translucent appearance of human skin. To accurately simulate subsurface scattering in multilayered materials, ...