检索结果-南通市图书馆

Flow-aware synthesis: A generic motion model for video frame interpolation

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第3期7卷 393-405页

作者： Jinbo Xing Wenbo Hu Yuechen Zhang tien-tsin wong Department of Computer Science and Engineering the Chinese University of Hong KongHong Kong SARChina Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesChina

A popular and challenging task in video research,frame interpolation aims to increase the frame rate of *** existing methods employ a fixed motion model,e.g.,linear,quadratic,or cubic,to estimate the intermediate warping ***,such fixed motion models cannot well represent the complicated non-linear motions in the real world or rendered ***,we present an adaptive flow prediction module to better approximate the complex motions in ***,interpolating just one intermediate frame between consecutive input frames may be insufficient for complicated non-linear *** enable multi-frame interpolation,we introduce the time as a control variable when interpolating frames between original ones in our generic adaptive flow prediction *** and quantitative experimental results show that our method can produce high-quality results and outperforms the existing stateof-the-art methods on popular public datasets.

关键词： flow-aware generic motion model video frame interpolation

Boundary-aware texture region segmentation from manga

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2017年第1期3卷 61-71页

作者： Xueting Liu Chengze Li tien-tsin wong The Chinese University of Hong Kong Hong KongChina Shenzhen Research Institute the Chinese University ofHong KongShenzhenChina

Due to the lack of color in manga(Japanese comics), black-and-white textures are often used to enrich visual experience. With the rising need to digitize manga, segmenting texture regions from manga has become an indispensable basis for almost all manga processing, from vectorization to colorization. Unfortunately, such texture segmentation is not easy since textures in manga are composed of lines and exhibit similar features to structural lines(contour lines). So currently, texture segmentation is still manually performed, which is labor-intensive and time-consuming. To extract a texture region, various texture features have been proposed for measuring texture similarity, but precise boundaries cannot be achieved since boundary pixels exhibit different features from inner pixels. In this paper, we propose a novel method which also adopts texture features to estimate texture regions. Unlike existing methods, the estimated texture region is only regarded an initial, imprecise texture region. We expand the initial texture region to the precise boundary based on local smoothness via a graph-cut formulation. This allows our method to extract texture regions with precise boundaries. We have applied our method to various manga images and satisfactory results were achieved in all cases.

关键词： manga texture segmentation

TransHist:Occlusion-robust shape detection in cluttered images

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2018年第2期4卷 161-172页

作者： Chu Han Xueting Liu Lok Tsun Sinn tien-tsin wong The Chinese University of Hong Kong Hong Kong China.

Shape matching plays an important role in various computer vision and graphics applications such as shape retrieval, object detection, image editing,image retrieval, etc. However, detecting shapes in cluttered images is still quite challenging due to the incomplete edges and changing perspective. In this paper, we propose a novel approach that can efficiently identify a queried shape in a cluttered image. The core idea is to acquire the transformation from the queried shape to the cluttered image by summarising all pointto-point transformations between the queried shape and the image. To do so, we adopt a point-based shape descriptor, the pyramid of arc-length descriptor(PAD),to identify point pairs between the queried shape and the image having similar local shapes. We further calculate the transformations between the identified point pairs based on PAD. Finally, we summarise all transformations in a 4 D transformation histogram and search for the main cluster. Our method can handle both closed shapes and open curves, and is resistant to partial occlusions. Experiments show that our method can robustly detect shapes in images in the presence of partial occlusions, fragile edges, and cluttered backgrounds.

关键词： shape matching shape detection transformation histogram

Region-based structure line detection for cartoons

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2015年第1期1卷 69-78页

作者： Xiangyu Mao Xueting Liu tien-tsin wong Xuemiao Xu The Chinese University of Hong Kong Shenzhen Research Institute The Chinese University of Hong Kong South China University of Technology

Cartoons are a worldwide popular visual entertainment medium with a long history. Nowadays,with the boom of electronic devices, there is an increasing need to digitize old classic cartoons as a basis for further editing, including deformation,colorization, etc. To perform such editing, it is essential to extract the structure lines within cartoon *** edge detection methods are mainly based on gradients. These methods perform poorly in the face of compression artifacts and spatially-varying line colors,which cause gradient values to become unreliable. This paper presents the first approach to extract structure lines in cartoons based on regions. Our method starts by segmenting an image into regions, and then classifies them as edge regions and non-edge regions. Our second main contribution comprises three measures to estimate the likelihood of a region being a non-edge *** measure darkness, local contrast, and *** the likelihoods become unreliable as regions become smaller, we further classify regions using both likelihoods and the relationships to neighboring regions via a graph-cut formulation. Our method has been evaluated on a wide variety of cartoon images, and convincing results are obtained in all cases.

关键词： computational cartoon edge detection image processing image segmentation line extraction region analysis

An improved parallel contrast-aware halftoning

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第12期14卷 918-929页

作者： Ling-yue LIU Wei CHEN tien-tsin wong Wen-ting ZHENG Wei-dong GENG State Key Lab of CAD & CG Zhejiang University Department of Computer Science and Engineering The Chinese University of Hong Kong

Digital image halftoning is a widely used technique. However, achieving high fidelity tone reproduction and structural preservation with low computational time cost remains a challenging problem. This paper presents a highly parallel algorithm to boost real-time application of serial structure-preserving error diffusion. The contrast-aware halftoning approach is one such technique with superior structure preservation, but it offers only a limited opportunity for graphics processing unit(GPU) acceleration. Our method integrates contrast-aware halftoning into a new parallelizable error-diffusion halftoning framework. To eliminate visually disturbing artifacts resulting from parallelization, we propose a novel multiple quantization model and space-filling curve to maintain tone consistency, blue-noise property, and structure consistency. Our GPU implementation on a commodity personal computer achieves a real-time performance for a moderately sized image. We demonstrate the high quality and performance of the proposed approach with a variety of examples, and provide comparisons with state-of-the-art methods.

关键词： Digital image halftoning Error diffusion GPU Quantization Space-filling curve

The Immersive Cockpit System for Capturing Natural Heritage

在线全文

学校读者我要写书评

暂无评论

系统仿真学报 2003年第3期15卷 306-309,314页

作者： Wai-Kwan Tang, tien-tsin wong, Pheng-Ann Heng Department of Computer Science & Engineering The Chinese University of Hong Kong Department of Computer Science & Engineering The Chinese University of HongKong

When the damage to a natural heritage is unavoidable, recording the natural heritage before damage may be the only way we can achieve to preserve the heritage in digital format. In this paper, we introduce a video-based tele-immersive system, called the Immersive Cockpit. It captures live videos from the interested site and recreates an immersive environment at the remote site where the user situates. With this system, users/audiences can immerse into the recreated natural heritage even the heritage no longer exists. The design goals of our system are real-time, live, low-cost and scalable. We stitch multiple video streams captured from ordinary CCD cameras to generate a panoramic video. To avoid being blocked by the supporting frame, we allow a flexible placement of cameras. This approach trades the accuracy of the generated panorama image for a larger field-of-view. The panoramic video is presented on an immersive display which covers the field-of-view of the viewer. We discuss how to correctly present the panoramic video on this non-planar immersive display screen by sweet spot relocation. We also present the result and the performance evaluation of the system.

关键词：多媒体应用浸入Cockpit系统浸入显示基于图像远程浸入系统实时全景

The electroweak monopole–antimonopole pair in the standard model

在线全文

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2024年第3期76卷 113-119页

作者： Dan Zhu Khai-Ming wong Guo-Quan wong School of Physics Universiti Sains Malaysia11800 USMPenangMalaysia

We present the first numerical solution that corresponds to a pair of Cho–Maison monopoles and antimonopoles(MAPs) in the SU(2) × U(1) Weinberg–Salam(WS) *** monopoles are finitely separated,while each pole carries a magnetic charge ±4π/*** positive pole is situated in the upper hemisphere,whereas the negative pole is in the lower *** Cho–Maison MAP is investigated for a range of Weinberg angles,0.4675≤ tan θ_(W)≤10,and Higgs self-coupling,0 ≤ β ≤ *** magnetic dipole moment(μm) and pole separation(d_(z)) of the numerical solutions are calculated and *** total energy of the system,however,is infinite due to point singularities at the locations of monopoles.

关键词： magnetic monopole Cho-Maison monopole Weinberg-Salam model

Synthetic brochosomes:Design,synthesis,and applications

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第2期17卷 734-742页

作者： Lin Wang Jinsol Choi Tak-Sing wong Department of Mechanical Engineering The Pennsylvania State UniversityUniversity ParkPA 16802USA Materials Research Institute The Pennsylvania State UniversityUniversity ParkPA 16802USA Department of Biomedical Engineering The Pennsylvania State UniversityUniversity ParkPA 16802USA

Brochosomes,which are nanoscopic buckyball-shaped granules produced by leafhoppers,are one of the most intricate structures discovered in *** functions of brochosomes have been proposed but only a few have been experimentally validated due to the challenge of fabricating their synthetic *** in micro-and nanofabrication have recently led to the emergence of synthetic brochosomes,opening up new possibilities for innovative *** review explores the early discovery of natural brochosomes and their geometrical features,followed by the recent progress in fabricating synthetic brochosomes and their *** on future applications and challenges in the scalable manufacturing of synthetic brochosomes are discussed.

关键词： synthetic brochosomes leafhopper antireflection superhydrophobicity surface-enhanced Raman scattering photocatalyst energy harvesting

Artificial intelligence analysis of videos to augment clinical assessment:an overview

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2024年第4期19卷 717-718页

作者： David C.wong Stefan Williams University of Leeds Leeds Teaching Hospitals Trust LeedsUK

Observation is a fundamental part of the practice of clinical *** of movement is particularly important for the *** such as Parkinson’s disease,multiple sclerosis,stroke,epilepsy,and many others affect a person’s movement in characteristic *** some conditions,changes in the patient’s voice can be included in this-changes in sound caused by changes in the movements of *** clinician’s detection of a characteristic abnormality,and their judgment of its severity,plays a central role in both diagnosis and the assessment of prognosis or response to ***,that practice depends upon a limited resource of experienced *** addition,these experts are limited by human visual judgment,which cannot reliably or precisely detect and measure small or subtle changes in movement(Williams et al.,2023).

关键词： clinical epilepsy diagnosis