检索结果-南通市图书馆

NPRportrait 1.0:A three-level benchmark for non-photorealistic rendering of portraits

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第3期8卷 445-465页

作者： paul l.rosin Yu-Kun lai David Mould Ran Yi Itamar Berger lars Doyle Seungyong lee Chuan li Yong-Jin liu Amir Semmo Ariel Shamir Minjung Son Holger Winnemöller School of Computer Science and Informatics Cardiff UniversityCardiffUK School of Computer Science Carleton UniversityOttawaCanada Department of Computer Science and Technology Tsinghua UniversityBeijingChina Reichman University(the Interdisciplinary Center) HerzliyaIsrael Department of Computer Science and Engineering Pohang University of Science and TechnologyPohangRepublic of Korea lambda labs Inc.San FranciscoUSA Hasso Plattner Institute University of PotsdamPotsdamGermany Multimedia Processing laboratory Samsung Advanced Institute of TechnologySuwonRepublic of Korea Adobe Systems Inc.San JoseUSA

Recently,there has been an upsurge of activity in image-based non-photorealistic rendering(NPR),and in particular portrait image stylisation,due to the advent of neural style transfer(NST).However,the state of performance evaluation in this field is poor,especially compared to the norms in the computer vision and machine learning communities.Unfortunately,the task of evaluating image stylisation is thus far not well defined,since it involves subjective,perceptual,and aesthetic aspects.To make progress towards a solution,this paper proposes a new structured,threelevel,benchmark dataset for the evaluation of stylised portrait images.Rigorous criteria were used for its construction,and its consistency was validated by user studies.Moreover,a new methodology has been developed for evaluating portrait stylisation algorithms,which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the faces.We perform evaluation for a wide variety of image stylisation methods(both portrait-specific and general purpose,and also both traditional NPR approaches and NST)using the new benchmark dataset.

关键词： non-photorealistic rendering(NPR) image stylization style transfer portrait evaluation benchmark

Edge-Aware level Set Diffusion and Bilateral Filtering Reconstruction for Image Magnification

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2009年第4期24卷 734-744页

作者：黄华臧彧 paul l.rosin 齐春 School of Electronics and Information Engineering Xi'an Jiaotong University Xi'an 710049 China School of Computer Science Cardiff University Cardiff U.K.

In this paper we propose an image magnification reconstruction method. In recent years many interpolation algorithms have been proposed for image magnification, but all of them have defects to some degree, such as jaggies and blurring. To solve these problems, we propose applying post-processing which consists of edge-aware level set diffusion and bilateral filtering. After the initial interpolation, the contours of the image are identified. Next, edge-aware level set diffusion is applied to these significant contours to remove the jaggies, followed by bilateral filtering at the same locations to reduce the blurring created by the initial interpolation and level set diffusion. These processes produce sharp contours without jaggies and preserve the details of the image. Results show that the overall RMS error of our method barely increases while the contour smoothness and sharpness are substantially improved.

关键词： computer application image magnification reconstruction edge-aware level set diffusion bilateral filtering

在线全文

学校读者我要写书评

暂无评论

Preface

Journal of Computer Science & Technology 2022年第3期37卷 559-560页

作者：胡事民 paul l.rosin 邵天甲 Department of Computer Science and Technology Tsinghua UniversityBeijing School of Computer Science and Informatics Cardiff UniversityCardiff State Key laboratory of CAD&CG Zhejiang UniversityHangzhou

The Computational Visual Media(CVM)conference series is intended to provide a major international forum for exchanging novel research ideas and significant computational methods that either underpin or apply visual media.The primary goal is to promote the cross-disciplinary research to amalgamate aspects of computer graphics,computer vision,machine learning,image and video processing,visualization and geometric computing.The main topics of interest to CVM include classification,composition,retrieval,synthesis,cognition and understanding of visual media(e.g.,images,video,3D geometry).

关键词： computer graphics visual

Practical automatic background substitution for live video

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2017年第3期3卷 273-284页

作者： Haozhi Huang Xiaonan Fang Yufei Ye Songhai Zhang paul l.rosin Department of Computer Science Tsinghua University School of Computer Science and Informatics Cardiff University

In this paper we present a novel automatic background substitution approach for live video. The objective of background substitution is to extract the foreground from the input video and then combine it with a new background. In this paper, we use a color line model to improve the Gaussian mixture model in the background cut method to obtain a binary foreground segmentation result that is less sensitive to brightness differences. Based on the high quality binary segmentation results, we can automatically create a reliable trimap for alpha matting to refine the segmentation boundary. To make the composition result more realistic, an automatic foreground color adjustment step is added to make the foreground look consistent with the new background. Compared to previous approaches, our method can produce higher quality binary segmentation results, and to the best of our knowledge, this is the first time such an automatic and integrated background substitution system has been proposed which can run in real time, which makes it practical for everyday applications.

关键词： background substitution background replacement background subtraction alpha matting

3D computational modeling and perceptual analysis of kinetic depth effects

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2020年第3期6卷 265-277页

作者： Meng-Yao Cui Shao-Ping lu Miao Wang Yong-liang Yang Yu-Kun lai paul l.rosin TKlNDST CSNankai UniversityTianjinChina State Key laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijingChina Department of Computer Science University of BathUK School of Computer Science and Informatics Cardiff UniversityWalesUK

Humans have the ability to perceive kinetic depth effects, i.e., to perceived 3 D shapes from 2 D projections of rotating 3 D objects. This process is based on a variety of visual cues such as lighting and shading effects. However, when such cues are weak or missing, perception can become faulty, as demonstrated by the famous silhouette illusion example of the spinning dancer. Inspired by this, we establish objective and subjective evaluation models of rotated3 D objects by taking their projected 2 D images as input. We investigate five different cues: ambient luminance, shading, rotation speed, perspective, and color difference between the objects and background.In the objective evaluation model, we first apply3 D reconstruction algorithms to obtain an objective reconstruction quality metric, and then use quadratic stepwise regression analysis to determine weights of depth cues to represent the reconstruction quality. In the subjective evaluation model, we use a comprehensive user study to reveal correlations with reaction time and accuracy, rotation speed, and perspective. The two evaluation models are generally consistent, and potentially of benefit to inter-disciplinary research into visual perception and 3 D reconstruction.

关键词： rotation spinning rotating

Skeleton-based canonical forms for non-rigid 3D shape retrieval

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第3期2卷 231-243页

作者： David Pickup Xianfang Sun paul l.rosin Ralph R.Martin School of Computer Science and Informatics Cardiff University

The retrieval of non-rigid 3D shapes is an important task. A common technique is to simplify this problem to a rigid shape retrieval task by producing a bending-invariant canonical form for each shape in the dataset to be searched. It is common for these techniques to attempt to "unbend" a shape by applying multidimensional scaling(MDS) to the distances between points on the mesh, but this leads to unwanted local shape distortions. We instead perform the unbending on the skeleton of the mesh, and use this to drive the deformation of the mesh itself. This leads to computational speed-up, and reduced distortion of local shape detail. We compare our method against other canonical forms: our experiments show that our method achieves state-of-the-art retrieval accuracy in a recent canonical forms benchmark, and only a small drop in retrieval accuracy over the state-of-the-art in a second recent benchmark, while being significantly faster.

关键词： canonical forms shape retrieval skeletons pose invariance

BING: Binarized normed gradients for objectness estimation at 300fps

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第1期5卷 3-20页

作者： Ming-Ming Cheng Yun liu Wen-Yan lin Ziming Zhang paul l.rosin Philip H.S.Torr CCS Nankai University Institute for Infocomm Research MERl Cambridge Cardiff University University of Oxford

Training a generic objectness measure to produce object proposals has recently become of significant interest. We observe that generic objects with well-defined closed boundaries can be detected by looking at the norm of gradients, with a suitable resizing of their corresponding image windows to a small fixed size. Based on this observation and computational reasons, we propose to resize the window to 8 × 8 and use the norm of the gradients as a simple 64 D feature to describe it, for explicitly training a generic objectness measure. We further show how the binarized version of this feature, namely binarized normed gradients(BING), can be used for efficient objectness estimation, which requires only a few atomic operations(e.g., add, bitwise shift, etc.). To improve localization quality of the proposals while maintaining efficiency, we propose a novel fast segmentation method and demonstrate its effectiveness for improving BING's localization performance, when used in multithresholding straddling expansion(MTSE) postprocessing. On the challenging PASCAl VOC2007 dataset, using 1000 proposals per image and intersectionover-union threshold of 0.5, our proposal method achieves a 95.6% object detection rate and 78.6% mean average best overlap in less than 0.005 second per image.

关键词： object proposals objectness visual attention category agnostic proposals

Integration of multiple flexible electrodes for realtime detection of barrier formation with spatial resolution in a gut-on-chip system

在线全文

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第1期10卷 105-114页

作者： Mara lucchetti Gabriel Werr Sofia Johansson laurent Barbe léa Grandmougin paul Wilmes Maria Tenje luxembourg Centre for Systems Biomedicine(lCSB) University of LuxembourgEsch-sur-Alzette L-4362Luxembourg Division of Biomedical Engineering Department of Materials Science and EngineeringScience for Life LaboratoryUppsala University75121 UppsalaSweden Department of life Sciences and Medicine Faculty of ScienceTechnology and MedicineUniversity of LuxembourgEsch-sur-Alzette L-4362Luxembourg

In healthy individuals,the intestinal epithelium forms a tight barrier to prevent gut bacteria from reaching blood circulation.To study the effect of probiotics,dietary compounds and drugs on gut barrier formation and disruption,human gut epithelial and bacterial cells can be cocultured in an in vitro model called the human microbial crosstalk(HuMiX)gut-on-a-chip system.Here,we present the design,fabrication and integration of thin-film electrodes into the HuMiX platform to measure transepithelial electrical resistance(TEER)as a direct readout on barrier tightness in realtime.As various aspects of the HuMiX platform have already been set in their design,such as multiple compressible layers,uneven surfaces and nontransparent materials,a novel fabrication method was developed whereby thin-film metal electrodes were first deposited on flexible substrates and sequentially integrated with the HuMiX system via a transfer-tape approach.Moreover,to measure localized TEER along the cell culture chamber,we integrated multiple electrodes that were connected to an impedance analyzer via a multiplexer.We further developed a dynamic normalization method because the active measurement area depends on the measured TEER levels.The fabrication process and system setup can be applicable to other barrier-on-chip systems.As a proof-of-concept,we measured the barrier formation of a cancerous Caco-2 cell line in real-time,which was mapped at four spatially separated positions along the HuMiX culture area.

关键词： barrier system multiple

Improving Shape from Shading with Interactive Tabu Search

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2016年第3期31卷 450-462页

作者： Jing Wu paul l. rosin Xianfang Sun Ralph R. Martin School of Computer Science and Informatics Cardiff University Cardiff CF24 3AA U.K.

Optimisation based shape from shading （SFS） is sensitive to initialization： errors in initialization are a signifi- cant cause of poor overall shape reconstruction. In this paper, we present a method to help overcome this problem by means of user interaction. There are two key elements in our method. Firstly, we extend SFS to consider a set of initializations, rather than to use a single one. Secondly, we efficiently explore this initialization space using a heuristic search method, tabu search, guided by user evaluation of the reconstruction quality. Reconstruction results on both synthetic and real images demonstrate the effectiveness of our method in providing more desirable shape reconstructions.

关键词： shape from shading user interaction tabu search