Search For:

Displaying 1-42 out of 42 total
Modelling Reflections via Multiperspective Imaging
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingyi Yu, Leonard McMillan
Issue Date:June 2005
pp. 117-124
We present a novel method for analyzing reflections on arbitrary surfaces. We model reflections using a broader than usual class of imaging models, which include both perspective and multiperspective camera types. We provide an analytical framework to loca...
 
Harnessing Real-World Depth Edges with Multiflash Imaging
Found in: IEEE Computer Graphics and Applications
By Ramesh Raskar, Kar-Han Tan, Rogerio S. Feris, Matthew Turk, James Kobler, Jingyi Yu
Issue Date:January 2005
pp. 32-38
A method for capturing geometric features of real-world scenes relies on a simple modification of the capture setup: A multiflash camera is used with flashes strategically positioned to cast shadows along depth discontinuities in the scene, allowing effici...
 
A Rotational Stereo Model Based on XSlit Imaging
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jinwei Ye,Yu Ji,Jingyi Yu
Issue Date:December 2013
pp. 489-496
Traditional stereo matching assumes perspective viewing cameras under a translational motion: the second camera is translated away from the first one to create parallax. In this paper, we investigate a different, rotational stereo model on a special multi-...
 
Line Assisted Light Field Triangulation and Stereo Matching
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Zhan Yu,Xinqing Guo,Haibing Ling,Andrew Lumsdaine,Jingyi Yu
Issue Date:December 2013
pp. 2792-2799
Light fields are image-based representations that use densely sampled rays as a scene description. In this paper, we explore geometric structures of 3D lines in ray space for improving light field triangulation and stereo matching. The triangulation proble...
 
A Coprime Blur Scheme for Data Security in Video Surveillance
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Christopher Thorpe, Feng Li, Zijia Li, Zhan Yu,David Saunders, Jingyi Yu
Issue Date:December 2013
pp. 3066-3072
This paper presents a novel coprime blurred pair (CBP) model to improve data security in camera surveillance. While most previous approaches have focused on completely encrypting the video stream, we introduce a spatial encryption scheme by strategically b...
 
An analysis of color demosaicing in plenoptic cameras
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Zhan Yu, Jingyi Yu,A. Lumsdaine,T. Georgiev
Issue Date:June 2012
pp. 901-908
A plenoptic camera captures the 4D radiance about a scene. Recent practical solutions mount a microlens array on top of a commodity SLR to directly acquire these rays. However, they suffer from low resolution as hundreds of thousands of views need to be ca...
 
Angular domain reconstruction of dynamic 3D fluid surfaces
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jinwei Ye, Yu Ji, Feng Li, Jingyi Yu
Issue Date:June 2012
pp. 310-317
We present a novel and simple computational imaging solution to robustly and accurately recover 3D dynamic fluid surfaces. Traditional specular surface reconstruction schemes place special patterns (checkerboard or color patterns) beneath the fluid surface...
 
Dynamic fluid surface acquisition using a camera array
Found in: Computer Vision, IEEE International Conference on
By Yuanyuan Ding,Feng Li, Yu Ji,Jingyi Yu
Issue Date:November 2011
pp. 2478-2485
Acquiring dynamic 3D fluid surfaces is a challenging problem in computer vision. Single or stereo camera based solutions are sensitive to refraction distortions, fast fluid motions, and calibration errors. In this paper, we present a multi-view based solut...
 
Salient Region Detection by UFO: Uniqueness, Focusness and Objectness
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Peng Jiang,Haibin Ling,Jingyi Yu,Jingliang Peng
Issue Date:December 2013
pp. 1976-1983
The goal of saliency detection is to locate important pixels or regions in an image which attract humans' visual attention the most. This is a fundamental task whose output may serve as the basis for further computer vision tasks like segmentation, resizin...
 
Design and Estimation of Coded Exposure Point Spread Functions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Scott McCloskey,Yuanyuan Ding,Jingyi Yu
Issue Date:October 2012
pp. 2071-2077
We address the problem of motion deblurring using coded exposure. This approach allows for accurate estimation of a sharp latent image via well-posed deconvolution and avoids lost image content that cannot be recovered from images acquired with a tradition...
 
Robust segmentation of biomedical figures for image-based document retrieval
Found in: 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
By Luis D. Lopez,Jingyi Yu,Catalina O. Tudor,Cecilia N. Arighi,Hongzhan Huang,K. Vijay-Shanker,Cathy H. Wu
Issue Date:October 2012
pp. 1-6
Figures play an important role in illustrating concepts, methodology and results in biomedicai literature. However, figures in biomedicai literature are often composed of multiple subfigures (panels), which may illustrate diverse methodologies or results. ...
 
An Automatic System for Extracting Figures and Captions in Biomedical PDF Documents
Found in: Bioinformatics and Biomedicine, IEEE International Conference on
By Luis D. Lopez,Jingyi Yu,Cecilia N. Arighi,Hongzhan Huang,Hagit Shatkay,Cathy Wu
Issue Date:November 2011
pp. 578-581
Figures in biomedical articles often constitute direct evidence of experimental results. Image analysis methods can be coupled with text-based methods to improve knowledge discovery. However, automatically harvesting figures along with their associated cap...
 
A theory of Coprime Blurred Pairs
Found in: Computer Vision, IEEE International Conference on
By Feng Li,Zijia Li,David Saunders, Jingyi Yu
Issue Date:November 2011
pp. 217-224
We present a new Coprime Blurred Pair (CBP) theory that may benefit a number of computer vision applications. A CBP is constructed by blurring the same latent image with two unknown kernels, where the two kernels are co-prime when mapped to bivariate polyn...
 
Blurred target tracking by Blur-driven Tracker
Found in: Computer Vision, IEEE International Conference on
By Yi Wu, Haibin Ling, Jingyi Yu, Feng Li, Xue Mei, Erkang Cheng
Issue Date:November 2011
pp. 1100-1107
Visual tracking plays an important role in many computer vision tasks. A common assumption in previous methods is that the video frames are blur free. In reality, motion blurs are pervasive in the real videos. In this paper we present a novel BLUr-driven T...
 
A theory of multi-perspective defocusing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanyuan Ding, Jing Xiao, Jingyi Yu
Issue Date:June 2011
pp. 217-224
We present a novel theory for characterizing defocus blurs in multi-perspective cameras such as catadioptric mirrors. Our approach studies how multi-perspective ray geometry transforms under the thin lens. We first use the General Linear Cameras (GLCs) to ...
 
Importance filtering for image retargeting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanyuan Ding, Jing Xiao, Jingyi Yu
Issue Date:June 2011
pp. 89-96
Content-aware image retargeting has attracted a lot of interests recently. The key and most challenging issue for this task is how to balance the tradeoff between preserving the important contents and minimizing the visual distortions on the consistency of...
 
Security Design on Construction Machinery Running Attention System
Found in: Cryptography, and Network Security, Data Mining and Knowledge Discovery, E-Commerce and Its Applications, and Embedded Systems, IACIS International Symposium on
By Li Pengfei, Zhao Jingyi, Yu Nana
Issue Date:October 2010
pp. 239-242
Through the analysis of CMRAS security design and security system security threats at all levels, including application layer, data access and processing layer, data layer, based on network layer, so as to formulate the corresponding security policies and ...
 
Recovering fluid-type motions using Navier-Stokes potential flow
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Feng Li, Liwei Xu, Philippe Guyenne, Jingyi Yu
Issue Date:June 2010
pp. 2448-2455
The classical optical flow assumes that a feature point maintains constant brightness across the frames. For fluid-type motions such as smoke or clouds, the constant brightness assumption does not hold, and accurately estimating the motion flow from their ...
 
Catadioptric projectors
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanyuan Ding, Jing Xiao, Kar-Han Tan, Jingyi Yu
Issue Date:June 2009
pp. 2528-2535
We present a catadioptric projector analogous to a catadioptric camera by combining a commodity digital projector with additional optical units. We show that, by using specially shaped reflectors/refractors, catadioptric projectors can offer an unprecedent...
 
Recovering specular surfaces using curved line images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanyuan Ding, Jingyi Yu, P. Sturm
Issue Date:June 2009
pp. 2326-2333
We present a new shape-from-distortion framework for recovering specular (reflective/refractive) surfaces. While most existing approaches rely on accurate correspondences between 2D pixels and 3D points, we focus on analyzing the curved images of 3D lines ...
 
Single-Image Vignetting Correction
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yuanjie Zheng, Stephen Lin, Chandra Kambhamettu, Jingyi Yu, Sing Bing Kang
Issue Date:December 2009
pp. 2243-2256
In this paper, we propose a method for robustly determining the vignetting function given only a single image. Our method is designed to handle both textured and untextured regions in order to maximize the use of available information. To extract vignettin...
 
Single-image vignetting correction using radial gradient symmetry
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanjie Zheng, Jingyi Yu, Sing Bing Kang, Stephen Lin, Chandra Kambhamettu
Issue Date:June 2008
pp. 1-8
In this paper, we present a novel single-image vignetting method based on the symmetric distribution of the radial gradient (RG). The radial gradient is the image gradient along the radial direction with respect to the image center. We show that the RG dis...
 
Recovering shape characteristics on near-flat specular surfaces
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanyuan Ding, Jingyi Yu
Issue Date:June 2008
pp. 1-8
We consider the problem of capturing shape characteristics on specular (refractive and reflective) surfaces that are nearly flat. These surfaces are difficult to model using traditional methods based on reconstructing the surface positions and normals. The...
 
A hybrid camera for motion deblurring and depth map super-resolution
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Feng Li, Jingyi Yu
Issue Date:June 2008
pp. 1-8
We present a hybrid camera that combines the advantages of a high resolution camera and a high speed camera. Our hybrid camera consists of a pair of low-resolution high-speed (LRHS) cameras and a single high-resolution low-speed (HRLS) camera. The LRHS cam...
 
FuzzyMatte: A computationally efficient scheme for interactive matting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanjie Zheng, Chandra Kambhamettu, Jingyi Yu, Thomas Bauer, Karl Steiner
Issue Date:June 2008
pp. 1-8
In this paper, we propose an online interactive matting algorithm, which we call FuzzyMatte. Our framework is based on computing the fuzzy connectedness (FC) [20] from each unknown pixel to the known foreground and background. FC effectively captures the a...
 
Lung Nodule Growth Analysis from 3D CT Data with a Coupled Segmentation and Registration Framework
Found in: Computer Vision, IEEE International Conference on
By Yuanjie Zheng, Karl Steiner, Thomas Bauer, Jingyi Yu, Dinggang Shen, Chandra Kambhamettu
Issue Date:October 2007
pp. 1-8
In this paper we propose a new framework to simultaneously segment and register lung and tumor in serial CT data. Our method assumes nonrigid transformation on lung deformation and rigid structure on the tumor. We use the B-Spline-based nonrigid transforma...
 
Robust Tracking and Stereo Matching under Variable Illumination
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingdan Zhang, Leonard McMillan, Jingyi Yu
Issue Date:June 2006
pp. 871-878
Illumination inconsistencies cause serious problems for classical computer vision applications such as tracking and stereo matching. We present a new approach to model illumination variations using an Illumination Ratio Map (IRM). An IRM computes the inten...
 
Multiperspective Projection and Collineation
Found in: Computer Vision, IEEE International Conference on
By Jingyi Yu, Leonard McMillan
Issue Date:October 2005
pp. 580-587
<p>We present theories of multiperspective projection and collineation. Given an arbitrary multiperspective imaging system that captures smoothly varying set of rays, we show how to map the rays onto a 2D ray manifold embedded in a 4D linear vector s...
 
Scan Light Field Rendering
Found in: Computer Graphics and Applications, Pacific Conference on
By Jingyi Yu, Leonard McMillan, Steven Gortler
Issue Date:October 2002
pp. 137
In this paper we present a new variant of the light field representation that supports improved image reconstruction by accomodating sparse correspondence information. This places our representation somewhere between a pure, tweo-plane parameterized, light...
 
Nonlinear Camera Response Functions and Image Deblurring: Theoretical Analysis and Practice
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yu-Wing Tai, Xiaogang Chen, Sunyeong Kim, Seon Joo Kim, Feng Li, Jie Yang, Jingyi Yu,Y. Matsushita,M. S. Brown
Issue Date:October 2013
pp. 2498-2512
This paper investigates the role that nonlinear camera response functions (CRFs) have on image deblurring. We present a comprehensive study to analyze the effects of CRFs on motion deblurring. In particular, we show how nonlinear CRFs can cause a spatially...
 
Reconstructing Gas Flows Using Light-Path Approximation
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yu Ji,Jinwei Ye,Jingyi Yu
Issue Date:June 2013
pp. 2507-2514
Transparent gas flows are difficult to reconstruct: the refractive index field (RIF) within the gas volume is uneven and rapidly evolving, and correspondence matching under distortions is challenging. We present a novel computational imaging solution by ex...
 
Manhattan Scene Understanding via XSlit Imaging
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jinwei Ye,Yu Ji,Jingyi Yu
Issue Date:June 2013
pp. 81-88
A Manhattan World (MW) is composed of planar surfaces and parallel lines aligned with three mutually orthogonal principal axes. Traditional MW understanding algorithms rely on geometry priors such as the vanishing points and reference (ground) planes for g...
 
Fast Patch-Based Denoising Using Approximated Patch Geodesic Paths
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Xiaogang Chen,Sing Bing Kang,Jie Yang,Jingyi Yu
Issue Date:June 2013
pp. 1211-1218
Patch-based methods such as Non-Local Means (NLM) and BM3D have become the de facto gold standard for image denoising. The core of these approaches is to use similar patches within the image as cues for denoising. The operation usually requires expensive p...
 
A hybrid image-CAD based system for modeling realistic hairstyles
Found in: Proceedings of the 18th meeting of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D '14)
By Jingyi Yu, Xiaogang Chen, Xuan Yu, Zhan Yu
Issue Date:March 2014
pp. 63-70
Generating realistic hairstyles is critical in modeling human characters in computer games and feature films. State-of-the-art geometric modeling tools demand extensive user efforts and artistic skills. Image-based approaches attempt to automate the modeli...
     
A framework for rendering complex scattering effects on hair
Found in: Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D '12)
By Takahiro Harada, Xuan Yu, Jason C. Yang, Jingyi Yu, Justin Hensley
Issue Date:March 2012
pp. 111-118
The appearance of hair plays a critical role in synthesizing realistic looking human characters. However, due to the high complexity in hair geometry and the scattering nature of hair fibers, rendering hair with photorealistic quality and at interactive sp...
     
Line-art illustration of dynamic and specular surfaces
Found in: ACM Transactions on Graphics (TOG)
By Jingyi Yu, Seungyong Lee, Xuan Yu, Yongjin Kim
Issue Date:December 2008
pp. 1-49
Line-art illustrations are effective tools for conveying shapes and shading of complex objects. We present a set of new algorithms to render line-art illustrations of dynamic and specular (reflective and refractive) surfaces. We first introduce a real-time...
     
Multiperspective modeling, rendering, and imaging
Found in: ACM SIGGRAPH ASIA 2008 courses (SIGGRAPH Asia '08)
By Jingyi Yu, Leonard McMillan, Peter Sturm
Issue Date:December 2008
pp. 1-36
A perspective image represents the spatial relationships of objects in a scene as they appear from a single viewpoint. In contrast, a multiperspective image combines what is seen from several viewpoints into a single image. Despite their incongruity of vie...
     
Geometric modeling using focal surfaces
Found in: ACM SIGGRAPH 2007 sketches on XX (SIGGRAPH '07)
By Jingyi Yu, Leonard McMillan, Steve Gortler, Xianfeng Gu, Xiaotian Yin
Issue Date:August 2007
pp. 70-es
The differential geometry of smooth three-dimensional surfaces can be interpreted from one of two perspectives: in terms of oriented frames located on the surface, or in terms of a pair of associated focal surfaces. These focal surfaces are swept by the lo...
     
Image fusion for context enhancement and video surrealism
Found in: ACM SIGGRAPH 2005 Courses (SIGGRAPH '05)
By Adrian Ilie, Jingyi Yu, Ramesh Raskar
Issue Date:July 2005
pp. 4-es
We present a class of image fusion techniques to automatically combine images of a scene captured under different illumination. Beyond providing digital tools for artists for creating surrealist images and videos, the methods can also be used for practical...
     
Non-photorealistic camera: depth edge detection and stylized rendering using multi-flash imaging
Found in: ACM SIGGRAPH 2005 Courses (SIGGRAPH '05)
By Jingyi Yu, Kar-Han Tan, Matthew Turk, Ramesh Raskar, Rogerio Feris
Issue Date:July 2005
pp. 2-es
We present a non-photorealistic rendering approach to capture and convey shape features of real-world scenes. We use a camera with multiple flashes that are strategically positioned to cast shadows along depth discontinuities in the scene. The projective-g...
     
Real-time reflection mapping with parallax
Found in: Proceedings of the 2005 symposium on Interactive 3D graphics and games (SI3D '05)
By Jason Yang, Jingyi Yu, Leonard McMillan
Issue Date:April 2005
pp. 133-138
We present a novel algorithm to efficiently render accurate reflections on programmable graphics hardware. Our algorithm overcomes problems that commonly occur in environment mapping such as the lack of motion parallax and inaccuracies when objects are clo...
     
Non-photorealistic camera: depth edge detection and stylized rendering using multi-flash imaging
Found in: ACM Transactions on Graphics (TOG)
By Jingyi Yu, Kar-Han Tan, Matthew Turk, Ramesh Raskar, Rogerio Feris
Issue Date:August 2004
pp. 679-688
We present a non-photorealistic rendering approach to capture and convey shape features of real-world scenes. We use a camera with multiple flashes that are strategically positioned to cast shadows along depth discontinuities in the scene. The projective-g...
     
 1