非真实感绘制技术研究进展

作为与真实感图形学相对应的图形学分支,非真实感绘制技术近年来受到人们的关注并已成为计算机图形学的研究热点之一,其研究成果已在计算机动画产业.计算机艺术和科学资料插图绘制等领域得到了广泛的应用.对非真实感绘制的相关技术进行了综述,首先介绍了非真实感绘制的发展过程,然后以不同艺术效果的模拟为线索对非真实感绘制技术进行了分类,并对各类技术的特点、发展状况和主要算法进行了分析和讨论,同时对非真实感绘制中所使用的特殊技术进行了分类讨论.最后对非真实感绘制技术的未来发展进行了展望.     

Interactive Control over Temporal Consistency while Stylizing Video Streams

Image stylization has seen significant advancement and widespread interest over the years, leading to the development of a multitude of techniques. Extending these stylization techniques, such as Neural Style Transfer (NST), to videos is often achieved by applying them on a per-frame basis. However, per-frame stylization usually lacks temporal consistency, expressed by undesirable flickering artifacts. Most of the existing approaches for enforcing temporal consistency suffer from one or more of the following drawbacks: They (1) are only suitable for a limited range of techniques, (2) do not support online processing as they require the complete video as input, (3) cannot provide consistency for the task of stylization, or (4) do not provide interactive consistency control. Domain-agnostic techniques for temporal consistency aim to eradicate flickering completely but typically disregard aesthetic aspects. For stylization tasks, however, consistency control is an essential requirement as a certain amount of flickering adds to the artistic look and feel. Moreover, making this control interactive is paramount from a usability perspective. To achieve the above requirements, we propose an approach that stylizes video streams in real-time at full HD resolutions while providing interactive consistency control. We develop a lite optical-flow network that operates at 80 Frames per second (FPS) on desktop systems with sufficient accuracy. Further, we employ an adaptive combination of local and global consistency features and enable interactive selection between them. Objective and subjective evaluations demonstrate that our method is superior to state-of-the-art video consistency approaches. maxreimann.github.io/stream-consistency     

Region-based bas-relief generation from a single image

Bas-relief is an art form part way between sculpture and drawing. In this paper, we present an algorithm for generating a bas-relief from a single image, inspired by the process that artists use to create reliefs. We do not aim to recover exact depth values for objects in the image, which is a tricky computer vision problem, requiring assumptions that are rarely satisfied. Instead, we determine layers based on relative depth ordering of objects (and their parts) in the image, and use this information to construct surfaces in the 3D relief model. Feature lines are extracted and used to build a new region-based representation of the input image. During surface construction, a base surface is first generated; it is then augmented using both intensity and gradient information from the original image. To prevent depth errors arising due to augmentation, a feedback process is used to refine the output. Our experimental results show the generated bas-reliefs have smooth boundaries with appropriate height relationships, a key property of bas-reliefs created by artists. We demonstrate that our algorithm works well for a range of input images, including human faces, flowers and animals.     

Some algorithms for image enhancement incorporating human visual response

Any image processing technique which is used to improve the appearance of an image for human perception or machine analysis should incorporate the characteristics of the human visual system. One of the major characteristics of the human visual system is the logarithmic response to light intensity, which we have attempted to include in this paper. Some new algorithms for image enhancement, edge detection and smoothing have been described and their results are presented. Only the edge detection technique is space-variant. All the techniques are simple and economical, and can be supplied to each pixel in parallel.     

Recovering 3D human pose based on biomechanical constraints,postures comfort and image shading

This paper presents a new model to identify 3D human poses in pictures, given a single input image. The proposed approach is based on a well known model found in the literature, including improvements in terms of biomechanical restrictions aiming to reduce the number of 3D possible postures that correctly represent the pose in the 2D image. Since the generated set of poses can have more than one possible posture, we propose a ranking system in order to suggest the best generated postures according to a “comfort” criterion and shading characteristics in the image as well. The comfort criterion adopts assumptions in terms of pose equilibrium, while the shading criterion eliminates the ambiguities of postures taken into account the image illumination. We must emphasize that the removal of ambiguous 3D poses related to a single image is the main focus of this work. The achieved results were analyzed w.r.t. visual inspection of users as well as a state of the art technique and indicate that our model contributed in some way to the solution of that challenge problem.     

Artistic minimal rendering with lines and blocks

Many non-photorealistic rendering techniques exist to produce artistic effects from given images. Inspired by various artists, interesting effects can be produced by using a minimal rendering, where the minimum refers to the number of tones as well as the number and complexity of the primitives used for rendering. Our method is based on various computer vision techniques, and uses a combination of refined lines and blocks (potentially simplified), as well as a small number of tones, to produce abstracted artistic rendering with sufficient elements from the original image. We also considered a variety of methods to produce different artistic styles, such as colour and 2-tone drawings, and use semantic information to improve renderings for faces. By changing some intuitive parameters a wide range of visually pleasing results can be produced. Our method is fully automatic. We demonstrate the effectiveness of our method with extensive experiments and a user study.     

Automatically mimicking unique hand-drawn pencil lines

In applications such as architecture, early design sketches containing accurate line drawings often mislead the target audience. Approximate human-drawn sketches are typically accepted as a better way of demonstrating fundamental design concepts. To this end we have designed an algorithm that creates lines that perceptually resemble human-drawn lines. Our algorithm works directly with input point data and a physically based mathematical model of human arm movement. Our algorithm generates unique lines of arbitrary length given the end points of a line, without relying on a database of human-drawn lines. We found that an observational analysis obtained through various user studies of human lines made a bigger impact on the algorithm than a statistical analysis. Additional studies have shown that the algorithm produces lines that are perceptually indistinguishable from that of a hand-drawn straight pencil line. A further expansion to the system resulted in mimicked dashed lines.     

A perceptual image quality index based on global and double-random window similarity

As one of indispensable steps in vision applications, the evaluation of the perceptual quality of an image attracts significant attention in recent years. This paper presents an image quality assessment algorithm using global and local similarities as two complementary aspects. It is based on two assumptions: (1) The evaluation of information in double-random local windows can capture the quality of an image accurately. (2) This method is highly consistent with human visual system in response to visual stimuli. The final quality index is obtained by combining two components, where the local quality score is calculated by comparing various features in double-random windows, and the global quality score is obtained pixel by pixel in the image. Experimental results on four large-scale benchmark databases show the effective and stable performance of the proposed method.     

Wavelet-based image watermarking with visibility range estimation based on HVS and neural networks

This work proposes a wavelet-based image watermarking (WIW) technique, based on the human visible system (HVS) model and neural networks, for image copyright protection. A characteristic of the HVS, which is called the just noticeable difference (JND) profile, is employed in the watermark embedding to enhance the imperceptibility of the technique. First, we derive the allowable visibility ranges of the JND thresholds for all coefficients of a wavelet-transformed image. The WIW technique exploits the ranges to compute the adaptive strengths to be superimposed in the wavelet coefficients while embedding watermarks. An artificial neural network (ANN) is then used to memorize the relationships between the original wavelet coefficients and its watermark version. Consequently, the trained ANN is utilized for estimating the watermark without the original image. Many existing schemes require the original image to be involved in the calculation of the JND profile of the image. Finally, computer simulations demonstrate that both transparency and robustness of the WIW technique are superior to that of other proposed methods.     

Fourier implementation of Poisson image editing

Poisson editing, introduced in 2003, is becoming a technique with major applications in many different domains of image processing and computer graphics. This letter presents an exact and fast Fourier implementation of the Poisson editing equation proposed in (Pérez et al., 2003). The proposed algorithm can handle well all Poisson editing methods that are currently implemented with finite differences and multigrid methods. But it also authorizes fast complex editing strategies where the edited region is obtained by an algorithm instead of a manual selection. The selected region can therefore have a complex topology without additional computational cost. In this letter the proposed method is applied to a classic local contrast enhancement principle introduced in (Caselles et al., 1999). The manual selection of the dark regions is replaced by a lower threshold and the method becomes fast, efficient, level-line preserving, and interactive. The proposed method can be tried on line on any uploaded image at http://www.ipol.im/pub/demo/lmps_selective_contrast_adjustment/.     

Spatially varying image based lighting using HDR-video

Illumination is one of the key components in the creation of realistic renderings of scenes containing virtual objects. In this paper, we present a set of novel algorithms and data structures for visualization, processing and rendering with real world lighting conditions captured using High Dynamic Range (HDR) video. The presented algorithms enable rapid construction of general and editable representations of the lighting environment, as well as extraction and fitting of sampled reflectance to parametric BRDF models. For efficient representation and rendering of the sampled lighting environment function, we consider an adaptive (2D/4D) data structure for storage of light field data on proxy geometry describing the scene. To demonstrate the usefulness of the algorithms, they are presented in the context of a fully integrated framework for spatially varying image based lighting. We show reconstructions of example scenes and resulting production quality renderings of virtual furniture with spatially varying real world illumination including occlusions.     

Parameterization,Feature Extraction and Binary Encoding for the Visualization of Tree-Like Structures

The study of vascular structures, using medical 3D models, is an active field of research. Illustrative visualizations have been applied to this domain in multiple ways. Researchers made the geometric properties of vasculature more comprehensive and augmented the surface with representations of multivariate clinical data. Techniques that head beyond the application of colour-maps or simple shading approaches require a surface parameterization, that is, texture coordinates, in order to overcome locality. When extracting 3D models, the computation of texture coordinates on the mesh is not always part of the data processing pipeline. We combine existing techniques to a simple parameterization approach that is suitable for tree-like structures. The parameterization is done w.r.t. to a pre-defined source vertex. For this, we present an automatic algorithm, that detects the tree root. The parameterization is partly done in screen-space and recomputed per frame. However, the screen-space computation comes with positive features that are not present in object-space approaches. We show how the resulting texture coordinates can be used for varying hatching, contour parameterization, display of decals, as additional depth cues and feature extraction. A further post-processing step based on parameterization allows for a segmentation of the structure and visualization of its tree topology.     

A scalable,real-time,image processing pipeline

To speed up image processing in the field of robot vision and industrial inspection, a pipeline element that can perform fast cellular logic operations was made. This cellular logic processing element (CLPE) can process binary images with a speed of 100ns per pixel. The processing element is a CMOS VLSI device. It includes a writable logic array for storing sets of 3 × 3 structuring elements that define the cellular logic operations. This paper describes how such CLPEs can be used for building a pipeline for mixed gray-value processing and cellular logic processing.     

Skeleton-based image warping

Image warping refers to the 2D resampling of a source image onto a target image. Despite the variety of techniques proposed, a large class of image warping problems remains inadequately solved: mapping between two images which are delimited by arbitrary, closed, planar curves, e.g., handdrawn curves. This paper describes a novel algorithm to perform image warping among arbitrary planar shapes whose boundary correspondences are known. A generalized polar coordinate parameterization is introduced to facilitate an efficient mapping procedure. Images are treated as collections of interior layers, extracted via a thinning process. Mapping these layers between the source and target images generates the 2D resampling grid that defines the warping. The thinning operation extends the standard polar coordinate representation to deal with arbitrary shapes.     

基于FPGA+DSP的实时图像处理系统设计与实现

针对图像处理系统计算量大、实时性高和体积小的要求,研制了一种以DSP为主处理器FPGA为辅处理器的高性能实时图像处理系统.利用这两种芯片的各自特点,将算法分成两部分分别交由FPGA和DSP处理,大大提高了算法的效率.系统具有结构简单易于实现和运用方便灵活的特点,加载上相应的程序之后能实现对所获取的图像跟踪、识别和匹配等处理方法.详细说明了系统的设计思路和硬件结构,并在硬件系统上进行了算法仿真及实验验证.实验结果表明:该系统实时性高,适应性好,能够满足设计要求.     

基于参考图像的色粉画模拟方法（CIDE 2013）

色粉画是一种极具表现力的绘画方式,本文提出一种基于参考图像色粉画效果模拟的非真实感绘制方法,其模拟过程分为铺底和细化二个阶段。在铺底阶段,利用mean-shift分割方法对参考图像进行分割获得区域和色调信息,并通过矢量场计算确定所得区域内笔画方向,在上述信息约束下通过对色粉画线画法以及侧面画法的模拟完成铺底工作;在细化阶段,针对参考图像所需突出的重要特征细节利用一致线条绘制方法获取,并通过色粉画点画法对其进行模拟。实验结果表明,通过上述二阶段模拟,本文所提方法能够快速高效的将参考图像转化为色粉画艺术化效果。     

HVS模型及其在静止图象压缩质量评价中的应用

图象质量尺度是最优化图象压缩算法参数和提高图象质量的重要依据 .建立在人类视觉模型 (HVS)基础之上的感知质量尺度作为主客观联系的桥梁 ,能有效地反映出人对图象失真在视觉上的感知 .近年来 ,有许多研究者借助人类视觉系统研究中的最新成果 ,深入分析了与图象质量密切相关的视觉感知特性 ,提出了大量效果不错的静止图象压缩感知质量尺度 ,并对视觉感知特性在图象质量尺度中的应用方法进行了较全面的综述 ,揭示了影响其图象质量预测准确性、鲁棒性的主要因素 ,给出了该领域的最新研究成果和未来发展方向 .     

Virtual stereo content rendering technology review for light-field display

Light field display (LFD) is considered as a promising technology to reconstruct the light rays’ distribution of the real 3D scene, which approximates the original light field of target displayed objects with all depth cues in human vision including binocular disparity, motion parallax, color hint and correct occlusion relationship. Currently, computer-generated content is widely used for the LFD system, therefore rich 3D content can be provided. This paper firstly introduces applications of light field technologies in display system. Additionally, virtual stereo content rendering techniques and their application scenes are thoroughly combed and pointed out its pros and cons. Moreover, according to the different characteristics of light field system, the coding and correction algorithms in virtual stereo content rendering techniques are reviewed. Through the above discussion, there are still many problems in the existing rendering techniques for LFD. New rendering algorithms should be introduced to solve the real-time light-field rendering problem for large-scale virtual scenes.