Line drawing via saliency map and ETF

Line drawing is a means of superior visual communication which can effectively convey useful information to viewers. Artists usually draw what they see rather than what exists, which means the most attractive object is emphasized while the rest are inhibited. Moreover, artists draw the whole object with coherent lines instead of fractured lines, which also contribute to the outstanding visual effect. From these perspectives, generating line drawings with saliency and coherence remains a great challenge. Existing line drawing generation methods ignore these important properties and cannot generate coherent lines in some cases since they do not take into account how artists draw a picture. To this end, a novel saliency-aware line drawing method was proposed to better grasp the viewer’s attention on an image. First, a saliency enhanced line extraction method combining saliency map and edge tangent flow was proposed to ensure the saliency and coherence of lines, especially in salient but low contrast areas. Then, the salient information was highlighted while irrelevant details were eliminated by inhibiting lines in less salient areas to enhance the saliency of the line drawing. Finally, the transparency of lines was adjusted to further emphasize important information. Various results showed that our method can generate line drawings with better visual saliency and coherence than the state-of-the-art methods.     

基于形状演化的线条画风格转换与变形

根据线条画和线条画中笔画的形状特征，运用平面形状演化理论对线条画和笔画的形状进行平滑或增强，并对宽度进行相应的调整，最后得到不同风格的线条画．该风格转换水需要任何样本，而且能够控制转换的程度，提高了线条画风格转换的自由度．     

边缘跟踪算法的图像线条画生成

给出一种基于边缘跟踪算法的图像线条画生成算法。该算法由边缘跟踪和线条画绘制两部分组成。在边缘跟踪中,提出基于相异性度量的边缘跟踪算法,以使利用边缘检测算子得到的边缘能够归类、连接;在线条画绘制过程中,引入非均匀B样条对不连续边缘进行插值并使用高斯平滑以获得连续光滑的边缘线条,然后以线条的曲率为依据,生成画笔,实现线条画的绘制。实验给出了本文方法生成的图像线条画的结果,实验结果表明,本文方法能够迅速快捷的生成较高质量的线条画。     

自适应的线条画绘制

目的 基于参考图像的线条画生成是非真实感绘制最为常见的应用之一。尽可能模拟艺术家的创作风格生成疏密得当、具有层次感的线条画是这类工作的主要目标和挑战。本文提出一个自适应线画图绘制算法。方法 首先,将场景图像分割成若干个区域,分别计算每个区域亮度的方差以及每个像素到边界的最小距离,将每个区域的方差和面积的比值作为该区域的复杂度。然后,计算能反映其显著视觉特征的边缘切向流场。最后,使用基于流的各向异性高斯差分滤波生成线条画。在构造边缘切向流时,每个位置的切向量由其邻域的切向量加权而得到。文中增加了一个新的系数项,对于邻域的任意一个位置,如果它和参考位置在区域分类中属同一个类别。则该位置的权值更大。基于流的高斯差分自适应滤波过程中,高斯差分滤波的尺度参数和复杂度以及到区域边界距离有关。细节越丰富,离边界越近,尺度参数取值越小,这样得到的边缘比较细,同时可以防止将相邻小细线条连接成粗线条。然后,将高斯差分滤波结果沿着流线方向进行高斯滤波,对于细节丰富的区域,边缘比较多,尺度参数取值比较小,所连接边缘比较短,可以减少错误边缘可能。结果 对生物、树林、建筑、山河等具有代表性的图像,采用本文算法进行自动实时进行线条绘制,实验结果表明,采用本文算法所生成的线条随着区域场景的复杂程度呈现不同粗细和浓淡的变化,具有一定的层次感。因而本文算法能生成视觉特征鲜明、风格化效果突出的线条画,且能处理各种复杂场景的图像。结论 本文自适应参数的线条画生成算法,其算法参数调节以及算法效果优于固定参数的算法,本文算法在处理日常生活中各类主题场景的图像时均能取得良好效果。     

SAR: Stroke Authorship Recognition

Are simple strokes unique to the artist or designer who renders them? If so, can this idea be used to identify authorship or to classify artistic drawings? Also, could training methods be devised to develop particular styles? To answer these questions, we propose the Stroke Authorship Recognition (SAR) approach, a novel method that distinguishes the authorship of 2D digitized drawings. SAR converts a drawing into a histogram of stroke attributes that is discriminative of authorship. We provide extensive classification experiments on a large variety of data sets, which validate SAR's ability to distinguish unique authorship of artists and designers. We also demonstrate the usefulness of SAR in several applications including the detection of fraudulent sketches, the training and monitoring of artists in learning a particular new style and the first quantitative way to measure the quality of automatic sketch synthesis tools.     

手绘图风格的三维模型线条渲染

现有的三维模型线条渲染方法,由于模型是网格结构,渲染得到线条图由大量的小线段组成,导致图形中有许多明显的棱角和孤立线段.提出了一种新的手绘图风格的三维模型线条渲染方法,将观察到的三维模型转化成简洁、自然的线条图.算法首先采用Suggestive Contours方法得到模型的特征线段集,通过分析线段的空间信息,将小线段连接成若干长线条,并用三次B样条曲线插值这些线条,然后引入B样条小波对线条进行简化.实验结果表明,本文的方法可以很好地连接这些线段集,得到平滑、简洁的手绘风格模型线条图.     

一种基于卡通画的线条画提取方法

给出了一种从卡通画中提取线条画的新方法。方法由三部分组成:线条提取、线条绘制和风格变换。给出了基于形态学方法细化图像,把结果中离散像素点深度优先遍历生成笔划路径集合,用不同细节来控制线条绘制,达到不同程度的抽象效果。给出了生成具有夸张风格的线条画的方法,实验结果显示用文中方法能从图像中抽象出生动的线条画。     

Animated 3D Line Drawings with Temporal Coherence

Producing traditional animation is a laborious task where the key drawings are first drawn by artists and thereafter inbetween drawings are created, whether it is by hand or computer‐assisted. Auto‐inbetweening of these 2D key drawings by computer is a non‐trivial task as 3D depths are missing. An alternate approach is to generate all the drawings by extracting lines directly from animated 3D models frame by frame, concatenating and rendering them together into an animation. However, animation quality generated using this straightforward method bears two problems. Firstly, the animation contains unsatisfactory visual artifacts such as line flickering and popping. This is especially pronounced when the lines are extracted using high‐order derivatives, such as ridges and valleys, from 3D models represented in triangle meshes. Secondly, there is a lack of temporal continuity as each drawing is generated without taking its neighboring drawings into consideration. In this paper, we propose an improved approach over the straightforward method by transferring extracted 3D line drawings of each frame into individual 3D lines and processing them along the time domain. Our objective is to minimize the visual artifacts and incorporate temporal relationship of individual lines throughout the entire animation sequence. This is achieved by creating correspondent trajectory of each line from each frame and applying global optimization on each trajectory. To realize this target, we present a fully automatic novel approach, which consists of (1) a line matching algorithm, (2) an optimizing algorithm, taking into account both the variations of numbers and lengths of 3D lines in each frame, and (3) a robust tracing method for transferring collections of line segments extracted from the 3D models into individual lines. We evaluate our approach on several animated model sequences to demonstrate its effectiveness in producing line drawing animations with temporal coherence.     

Labeling Line Drawings with Hidden-Part-Drawn of Planar Object with Trihedral Vertices

Although line drawings consist of only line segments on a plane, they convey much information about the three-dimensional object structures. For a computer interpreting line drawings, some intelligent mechanism is required to extract three-dimensional information from the two-dimensional line drawings. In this paper, a new labeling theory and method are proposed for the two-dimensional line drawing with hidden-part-draw of a three-dimensional planar object with trihedral vertices. Some rules for labeling line drawing are established. There are 24 kinds of possible junctions for line drawing with hidden-part-draw, in which there are 8 possible Y and 16 W junctions. The three problems are solved that Sugihara's line drawing labeling technique exists. By analyzing the projections of the holes in manifold planar object, we have put forward a labeling method for the line drawing. Our labeling theory and method can discriminate between correct and incorrect hidden-part-draw natural line drawings. The hidden-part-draw natural line drawings can be labeled correctly by our labeling theory and method, whereas the labeling theory of Sugihara can only label the hidden-part-draw unnatural line drawings in which some visible lines must be drawn as hidden lines, and some invisible lines must be drawn as continuous lines.     

梵高风格的笔触骨架线绘制方法研究及应用

将虚拟的数字图像转变为实体艺术作品的需求随着社会发展与日俱增,而梵高作为传奇艺术家,其风格被无数人效仿。利用基于笔刷的图像风格化技术,设计了一种模拟梵高绘画风格的笔触骨架线绘制算法,生成表示笔触抽象轨迹的图谱,用于油画、刺绣等真实艺术作品的辅助创作,提出的辐射方向梯度插值方法较好地模拟了梵高水波纹状的笔触方向布局。     

基于纹理和草图的图像铅笔画绘制

针对目前铅笔画生成方法中的线条不够灵活、纹理缺少方向感的问题,提出了一种基于带方向的纹理和线条草图将一幅图像转换为铅笔画风格的方法。首先,对输入图像进行直方图匹配得到图像的色调图,并将图像分割为多个区域,对每个区域,根据其颜色和形状计算其色调和方向,以此决定铅笔纹理的色调和方向;然后,通过可调整的线性卷积方法得到铅笔画的线条草图;最后,将纹理和草图结合得到铅笔画效果。运用提出的方法对不同类型的自然图像进行了铅笔画的转换,并与已有的线卷积积分方法和基于色调的方法进行了对比。实验结果表明带方向的区域纹理能更好地模拟手工铅笔画纹理的方向,可调整的线条能够更好地模拟手工铅笔画的线条的随意性和灵活性。     

基于样本区域的线条画风格转换

针对某些线条画存在多于一种风格的线条的情况,提出了一种利用线条画作为样本对任意线条画进行风格转换的方法。该方法基于指定的样本区域和目标区域,通过指定单位长度对笔划分段进行风格相似性比较,并引入旋转和缩放参数进行笔划的规范化表示。与已有的方法比较,该方法算法简单并能产生新的风格转换效果。     

Colorization of Line Drawings with Empty Pupils

Many studies have recently applied deep learning to the automatic colorization of line drawings. However, it is difficult to paint empty pupils using existing methods because the convolutional neural network are trained with pupils that have edges, which are generated from color images using image processing. Most actual line drawings have empty pupils that artists must paint in. In this paper, we propose a novel network model that transfers the pupil details in a reference color image to input line drawings with empty pupils. We also propose a method for accurately and automatically colorizing eyes. In this method, eye patches are extracted from a reference color image and automatically added to an input line drawing as color hints using our pupil position estimation network.     

Efficient and robust 3D line drawings using difference-of-Gaussian

Line drawings are widely used for sketches, animations, and technical illustrations because they are effective and easy to draw. The existing computer-generated lines, such as suggestive contours, apparent ridges, and demarcating curves, adopt the two-pass framework: in the first pass, certain geometric features or properties are extracted or computed in the object space; then in the second pass, the line drawings are rendered by iterating each polygonal face or edge. It is known these approaches are very sensitive to the mesh quality, and usually require appropriate preprocessing operations (e.g. smoothing, remeshing, etc.) to the input meshes. This paper presents a simple yet robust approach to generate view-dependent line drawings for 3D models. Inspired by the image edge detector, we compute the difference-of-Gaussian of illumination on the 3D model. With moderate assumption, we show all the expensive computations can be done in the pre-computing stage. Our method naturally integrates object- and image-spaces in that we compute the geometric features in the object space and then adopt a simple fragment shader to render the lines in the image space. As a result, our algorithm is more efficient than the existing object-space approaches, since the lines are generated in a single pass without iterating the mesh edges/faces. Furthermore, our method is more flexible and robust than the existing algorithms in that it does not require the preprocessing on the input 3D models. Finally, the difference-of-Gaussian operator can be extended to the anisotropic setting guided by local geometric features. The promising experimental results on a wide range of real-world models demonstrate the effectiveness and robustness of our method.     

工程扫描图象的直线整体识别算法

利用工程图纸的整体形状特性，提出了对扫描图象的直线整体识别算法，该算法对图象线条轮廓上的关键点进行了精确记录，并对它们进行了分析和处理。该算法不必单独处理线的交叉问题，但交叉点处的效果明显。它的基本思想是：首先检测原图象线宽，然后依据原图象线条的不同线宽，把原图象转化为一些由梯形块组成的条块图，并对不同的条块图分别进行整体识别     

Image-based pencil drawing synthesized using convolutional neural network feature maps

In most cases, the conventional pencil-drawing-synthesized methods were in terms of geometry and stroke, or only used classic edge detection method to extract image edge characters. In this paper, we propose a new method to produce pencil drawing from natural image. The synthesized result can not only generate pencil sketch drawing, but also can save the color tone of natural image and the drawing style is flexible. The sketch and style are learned from the edge of original natural image and one pencil image exemplar of artist’s work. They are accomplished through using the convolutional neural network feature maps of a natural image and an exemplar pencil drawing style image. Large-scale bound-constrained optimization (L-BFGS) is applied to synthesize the new pencil sketch whose style is similar to the exemplar pencil sketch. We evaluate the proposed method by applying it to different kinds of images and textures. Experimental results demonstrate that our method is better than conventional method in clarity and color tone. Besides, our method is also flexible in drawing style.     

具有层次素描纹理的素描画绘制方法

针对现有的计算机非真实感绘制(NPR)技术关于素描画的绘制方法的实现效果与手绘风格存在一定差异的问题,设计了一种能够产生层次素描纹理的方法,并将其与多像素宽边缘线条融合,生成具有层次感素描纹理的素描画。首先对原始图像做去噪、增强等预处理,用微分算子提取多像素宽的轮廓线条;再通过膨胀和腐蚀处理并将结果相减生成多层双边轮廓线条,用运动模糊处理多层双边线条得到素描纹理;最后融合边缘和素描纹理,得到素描效果图像。通过对不同特点的图像进行实验,证明该方法得到的素描画的效果比较接近手绘风格。     

A Visualization Framework and User Studies for Overloaded Orthogonal Drawings

Overloaded orthogonal drawing (OOD) is a recent graph visualization style specifically conceived for directed graphs. It merges the advantages of some popular drawing conventions like layered drawings and orthogonal drawings, and provides additional support for some common analysis tasks. We present a visualization framework called DAGView, which implements algorithms and graphical features for the OOD style. Besides the algorithm for acyclic digraphs, the DAGView framework implements extensions to visualize both digraphs with cycles and undirected graphs, with the additional possibility of taking into account user preferences and constraints. It also supports an interactive visualization of clustered digraphs, based on the use of strongly connected components. Moreover, we describe an experimental user study, aimed to investigate the usability of OOD within the DAGView framework. The results of our study suggest that OOD can be effectively exploited to perform some basic tasks of analysis in a faster and more accurate way when compared to other drawing styles for directed graphs.     

基于语义分割的简洁线条肖像画生成方法

针对目前主流的线条提取算法对于区域对比度不明显的边缘的检测能力较弱,且对于所有区域采用无差别、统一化的处理策略,所生成的线条画往往较复杂,非常不利于机器人机械臂绘图的问题,本文提出了一种基于语义分割的简洁线条肖像画生成方法(concise line portrait generation based on semantic segmentation, CLPG-SS)。首先,对人脸图像进行语义分割,将人脸划分为不同的区域,基于不同区域提取边缘轮廓与五官细节线条,进行边缘切向流优化,从而加强方向信息;在此基础上,利用线条图来生成调和图像,并利用优化后的边缘切向流、人脸语义分割结果以及调和图像,针对不同的分割区域调整线条提取方法的参数,实现对细节无关区域的线条过滤和细节重点区域的线条加强,生成简洁线条肖像画。实验结果表明:本文提出的CLPG-SS方法能够有效提取人脸主轮廓线条,并针对不同区域实现了对细节线条的针对性调节,提高了机器人机械臂的绘制效率。