基于BSSRDF模型回归人脸皮肤实时渲染

基于三层材质模型,利用双向表面散射反射分布函数,模拟光线在皮肤表面的散射效果。提出一种采用径向基函数神经网络对次表面散射剖面进行拟合的方法,以实现人脸皮肤真实感实时渲染。使用离线渲染的方式进行预计算,获取训练数据,进行训练,代替传统的渲染方式。实验证明,本文方法能有效减少冗余数据,以较快的速度收敛,并且很好地拟合离线渲染的结果。     

GPU-based rendering for deformable translucent objects

In this paper we introduce an approximate image-space approach for real-time rendering of deformable translucent models by flattening the geometry and lighting information of objects into textures to calculate multi-scattering in texture spaces. We decompose the process into two stages, called the gathering and scattering corresponding to the computations for incident and exident irradiance respectively. We derive a simplified illumination model for the gathering of the incident irradiance, which is amenable for deformable models using two auxiliary textures. In the scattering stage, we adopt two modes for efficient accomplishment of the view-dependent scattering. Our approach is implemented by fully exploiting the capabilities of graphics processing units (GPUs). It achieves visually plausible results and real-time frame rates for deformable models on commodity desktop PCs.     

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.      

雨雾天气下光线散射效果的实时绘制

提出一种适用于雨雾天气的天空光照的多粒子散射模型,实现了雨雾场景中大气散射效果及雨后彩虹的真实感绘制.同时,通过对传统点光源单散射模型公式的解析简化,实现了各向异性光源散射效果的实时绘制.最终实时绘制出多种不同条件下真实感较强的雨雾场景.     

A fast rendering method for clouds illuminated by lightning taking into account multiple scattering

Methods for rendering natural scenes are used in many applications such as virtual reality, computer games, and flight simulators. In this paper, we focus on the rendering of outdoor scenes that include clouds and lightning. In such scenes, the intensity at a point in the clouds has to be calculated by taking into account the illumination due to lightning. The multiple scattering of light inside clouds is an important factor when creating realistic images. However, the computation of multiple scattering is very time-consuming. To address this problem, this paper proposes a fast method for rendering clouds that are illuminated by lightning. The proposed method consists of two processes. First, basis intensities are prepared in a preprocess step. The basis intensities are the intensities at points in the clouds that are illuminated by a set of point light sources. In this precomputation, both the direct light and also indirect light (i.e., multiple scattering) are taken into account. In the rendering process, the intensities of clouds are calculated in real-time by using the weighted sum of the basis intensities. A further increase in speed is achieved by using a wavelet transformation. Our method achieves the real-time rendering of realistic clouds illuminated by lightning.     

球面全景图漫游算法研究

基于图像的绘制技术不仅可以弥补传统基于几何绘制技术的不足。而且能给出更丰富的图像显示。基于实际应用出发,提出并实现了一种球面全景图的漫游算法。通过重投影球面全景图的可视部分到视平面上,可以生成虚拟场景在不同视线方向上的透视视图。针对直接使用重投影不能满足实时绘制的问题,提出了基于查找表的优化策略。     

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, ...     

基于shader实现的光线透射效果

真实的模拟光线的透射效果是实时计算机图形学中一个非常令人关注的内容.对于这种自然现象的模拟所要达到的两个目标是真实性和实时性.为了达到这一要求,介绍了一种能够实时并且真实的模拟这种自然现象的算法,在Microsoft Visual Studio开发环境下,利用DirectX9.0软件包进行3D开发,并结合shader技术编程实现,运行的结果表明此算法是可行的和高效的.     

Automatic Image-Based Pencil Sketch Rendering

This paper presents an automatic image-based approach for converting greyscale images to pencil sketches,in which strokes follow the image features.The algorithm first extracts a dense direction field automatically using Logical/Linear operators which embody the drawing mechanism.Next,a reconstruction approach based on a sampling-and-interpolation scheme is introduced to generate stroke paths from the direction field.Finally,pencil strokes are rendered along the specified paths with consideration of image tone and artificial illumingation.As an important application,the technique is applied to render portraits from images with little user interaction.The experimental results demonstrate that the approach can automatically achieve copmelling pencil sketches from reference images.     

Texturing 3D Models of Real World Objects from Multiple Unregistered Photographic Views

As the efficiency of computer graphic rendering methods is increasing, generating realistic models is now becoming a limiting factor. In this paper we present a new technique to enhance already existing geometry models of real world objects with textures reconstructed from a sparse set of unregistered still photographs. The aim of the proposed technique is the generation of nearly photo-realistic models of arbitrarily shaped objects with minimal effort. In our approach, we require neither a prior calibration of the camera nor a high precision of the user's interaction. Two main problems have to be addressed of which the first is the recovery of the unknown positions and parameters of the camera. An initial estimate of the orientation is calculated from interactively selected point correspondences. Subsequently, the unknown parameters are accurately calculated by minimising a blend of objective functions in a 3D-2D projective registration approach. The key point of the proposed method of registration is a novel filtering approach which utilises the spatial information provided by the geometry model. Second, the individual images have to be combined yielding a set of consistent texture maps. We present a robust method to recover the texture from the photographs thereby preserving high spatial frequencies and eliminating artifacts, particularly specular highlights. Parts of the object not seen in any of the photographs are interpolated in the textured model. Results are shown for three complex example objects with different materials and numerous self-occlusions.     

基于图象的绘制技术

基于图象绘制技术是实现对虚拟场景建模和实时绘制的新的有效方法,可以克服传统的基于几何绘制方式中建立起初模型的困难和实时绘制计算在的缺陷。本文介绍和分析目前图象绘制技术的一些主要方法,并提出改进途径。     

飞行仿真中真实感三维云的快速绘制方法

近年来提出的云的真实感绘制算法大多采用纹理操作进行绘制,绘制算法复杂,渲染过程较长,对计算机硬件的要求高,不能完全满足飞行仿真的实时性要求。为解决上述问题,从光的单一散射出发,考虑云和大气粒子引起的光衰减率,采用阴影切片的方法分割体数据,在太阳照射方向上和视点观察方向上对切片数据进行分析,从而快速绘制出真实感三维云。仿真结果表示,生成的三维云效果真实,具有良好的实时性,能够满足飞行仿真及其他领域的要求。     

基于GPU的屏幕空间镜头水滴实时渲染

为了实时模拟真实性高的镜头水滴,提出一种在可编程图形硬件中实现的镜头水滴渲染新方法。首先三维场景被渲染到一张场景纹理,然后在GPU着色器中为镜头水滴产生不规则边缘接触曲线,使用该曲线快速构建水滴的曲面,最后采用曲面的表面信息并根据水滴的光学属性渲染出水滴的折射效果。采用该方法,可以实时地在屏幕上渲染出镜头水滴效果。使用GPU着色器进行渲染,可以在渲染出效果逼真的水滴的情况下,获得实时的帧率。采用光线折射物理方法渲染出的水滴的效果比直接使用纹理贴图方式获得的水滴的效果更逼真。     

虚拟手术中的模型实时绘制

实时的视觉反馈在虚拟手术中可以加强操作者的沉浸感。该文分析了体绘制和面绘制的优缺点,在系统实时性的要求下,实现了基于立体纹理映射的三维体模型的面绘制。算法在容许实时交互的同时,为操作者提供了真实感较强的视觉反馈。由于文中立体纹理生成及纹理坐标计算的特殊性,对虚拟手术中的拉压变形和切割等操作也能很好地处理。     

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.     

On-line Free-viewpoint Video： From Single to Multiple View Rendering

In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. We present a new VBR system that creates new views of a live dynamic scene. This system provides high quality images and does not require any background subtraction. Our method follows a plane-sweep approach and reaches real-time rendering using consumer graphic hardware, graphics processing unit （GPU）. Only one computer is used for both acquisition and rendering. The video stream acquisition is performed by at least 3 webcams. We propose an additional video stream management that extends the number of webcams to 10 or more. These considerations make our system low-cost and hence accessible for everyone. We also present an adaptation of our plane-sweep method to create simultaneously multiple views of the scene in real-time. Our system is especially designed for stereovision using autostereoscopic displays. The new views are computed from 4 webcams connected to a computer and are compressed in order to be transfered to a mobile phone. Using GPU programming, our method provides up to 16 images of the scene in real-time. The use of both GPU and CPU makes this method work on only one consumer grade computer.     

半透明三维物体表面光泽真实感实时渲染方法

针对具有半透明特性玉石的真实感渲染问题,提出一种利用高光层、漫反射层、透射层三层光照模型叠加的解决方法。首先对散射层结合漫反射剖面来模拟半透明玉石的次表面散射效果,提出一种可改变漫反射剖面的散射方法,表达不同种类玉石漫反射剖面的特点;然后对透射层利用预计算的本地厚度贴图结合高斯线性和,实现基于表面厚度光的透射效果,再在能量守恒的基础上与基于微平面的高光反射项进行叠加,得到一个基于三层光照模型的真实感半透明材质表现。实验结果表明,所提出的方法能实现不同种类半透明玉石真实感渲染,且在片面数达160万时可保证30帧/秒的实时效率。     

Single‐image Tomography: 3D Volumes from 2D Cranial X‐Rays

As many different 3D volumes could produce the same 2D x‐ray image, inverting this process is challenging. We show that recent deep learning‐based convolutional neural networks can solve this task. As the main challenge in learning is the sheer amount of data created when extending the 2D image into a 3D volume, we suggest firstly to learn a coarse, fixed‐resolution volume which is then fused in a second step with the input x‐ray into a high‐resolution volume. To train and validate our approach we introduce a new dataset that comprises of close to half a million computer‐simulated 2D x‐ray images of 3D volumes scanned from 175 mammalian species. Future applications of our approach include stereoscopic rendering of legacy x‐ray images, re‐rendering of x‐rays including changes of illumination, view pose or geometry. Our evaluation includes comparison to previous tomography work, previous learning methods using our data, a user study and application to a set of real x‐rays.     

Geocube – GPU accelerated real-time rendering of transparency and translucency

We present a new method based on GPU acceleration for real-time transparency and translucency rendering. Our method computes refraction at both the front and back sides of a transparent object, as well as internal reflection, thus delivering interactive realistic transparency effects on a commodity PC. The real-time performance is made possible by a new acceleration data structure, called geocube, that enables the use of GPU for fast ray-surface intersection testing. In addition, within the same framework, we introduce the novel use of the mip-map for a hierarchical representation of a sequence of key prefiltered environment maps to simulate translucency. By taking ray depth into account and using GPU to interpolate the key filtered maps to produce the desired blurring effects, we achieve real-time realistic translucency rendering of slightly scattering media that allows show-through of background details.     

真实感树木绘制技术研究

真实感树木绘制技术的研究是计算机真实感图形学的一个热点领域,因为树木复杂的细节结构使其在绘制上存在着相当大的困难.主要讨论了真实感树木的绘制方法,对国内外在该领域的工作成果进行了较为系统的介绍,并对各种绘制方法的优缺点进行了分析,最后展望了该技术的发展.