Search For:

Displaying 1-50 out of 86 total
Image deblurring using inertial measurement sensors
Found in: ACM Transactions on Graphics (TOG)
By C. Lawrence Zitnick, Neel Joshi, Richard Szeliski, Sing Bing Kang, C. Lawrence Zitnick, Neel Joshi, Richard Szeliski, Sing Bing Kang, C. Lawrence Zitnick, Neel Joshi, Richard Szeliski, Sing Bing Kang, C. Lawrence Zitnick, Neel Joshi, Richard Szeliski, Sing Bing Kang
Issue Date:July 2010
pp. 1-10
We present a deblurring algorithm that uses a hardware attachment coupled with a natural image prior to deblur images from consumer cameras. Our approach uses a combination of inexpensive gyroscopes and accelerometers in an energy optimization framework to...
     
Editor's Note
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih,Sing Bing Kang,Neil Lawrence,Jiri Matas,Max Welling
Issue Date:May 2012
pp. 833
No summary available.
 
Editor's Note
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih,Sing Bing Kang,Neil Lawrence,Jiri Matas,Max Welling
Issue Date:February 2012
pp. 209-210
No summary available.
 
Guest Editors' Introduction to the Special Section on Award-Winning Papers from the IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR 2009)
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Irfan Essa,Sing Bing Kang,Marc Pollefeys
Issue Date:December 2011
pp. 2339-2340
No summary available.
 
Editor's Note
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih,Sing Bing Kang,Jiri Matas,Max Welling
Issue Date:December 2011
pp. 2337-2340
No summary available.
 
Editor's Note
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih,Sing Bing Kang,Jiri Matas,Max Welling
Issue Date:November 2011
pp. 2129-2130
No summary available.
 
Editorial
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih, Zoubin Ghahramani, Sing Bing Kang, Jiri Matas
Issue Date:September 2011
pp. 1697-1698
No summary available.
 
Editor's Note
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih, Zoubin Ghahramani, Sing Bing Kang, Jiri Matas
Issue Date:May 2011
pp. 865-866
No summary available.
 
Depth Transfer: Depth Extraction from Video Using Non-Parametric Sampling
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kevin Karsch,Ce Liu,Sing Bing Kang
Issue Date:November 2014
pp. 1-1
We describe a technique that automatically generates plausible depth maps from videos using non-parametric depth sampling. We demonstrate our technique in cases where past methods fail (non-translating cameras and dynamic scenes). Our technique is applicab...
 
Single-Image Vignetting Correction from Gradient Distribution Symmetries
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yuanjie Zheng,Stephen Lin,Sing Bing Kang,Rui Xiao,James C. Gee,Chandra Kambhamettu
Issue Date:June 2013
pp. 1480-1494
We present novel techniques for single-image vignetting correction based on symmetries of two forms of image gradients: semicircular tangential gradients (SCTG) and radial gradients (RG). For a given image pixel, an SCTG is an image gradient along the tang...
 
Video Snapshots: Creating High-Quality Images from Video Clips
Found in: IEEE Transactions on Visualization and Computer Graphics
By K. Sunkavalli,N. Joshi, Sing Bing Kang,M. F. Cohen,H. Pfister
Issue Date:November 2012
pp. 1868-1879
We describe a unified framework for generating a single high-quality still image (
 
Image Restoration by Matching Gradient Distributions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Taeg Sang Cho,C. L. Zitnick,N. Joshi, Sing Bing Kang,R. Szeliski,W. T. Freeman
Issue Date:April 2012
pp. 683-694
The restoration of a blurry or noisy image is commonly performed with a MAP estimator, which maximizes a posterior probability to reconstruct a clean image from a degraded image. A MAP estimator, when used with a sparse gradient image prior, reconstructs p...
 
State of the Journal
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ramin Zabih,Sing Bing Kang,Jiri Matas,Max Welling;
Issue Date:January 2012
pp. 1-2
No summary available.
 
Noise suppression in low-light images through joint denoising and demosaicing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By P. Chatterjee,N. Joshi, Sing Bing Kang,Y. Matsushita
Issue Date:June 2011
pp. 321-328
We address the effects of noise in low-light images in this paper. Color images are usually captured by a sensor with a color filter array (CFA). This requires a demosaicing process to generate a full color image. The captured images typically have low sig...
 
Collaborative personalization of image enhancement
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By J. C. Caicedo,A. Kapoor, Sing Bing Kang
Issue Date:June 2011
pp. 249-256
While most existing enhancement tools for photographs have universal auto-enhancement functionality, recent research shows that users can have personalized preferences. In this paper, we explore whether such personalized preferences in image enhancement te...
 
A content-aware image prior
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Taeg Sang Cho, Neel Joshi, C. Lawrence Zitnick, Sing Bing Kang, Richard Szeliski, William T. Freeman
Issue Date:June 2010
pp. 169-176
In image restoration tasks, a heavy-tailed gradient distribution of natural images has been extensively exploited as an image prior. Most image restoration algorithms impose a sparse gradient prior on the whole image, reconstructing an image with piecewise...
 
Personalization of image enhancement
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sing Bing Kang, Ashish Kapoor, Dani Lischinski
Issue Date:June 2010
pp. 1799-1806
We address the problem of incorporating user preference in automatic image enhancement. Unlike generic tools for automatically enhancing images, we seek to develop methods that can first observe user preferences on a training set, and then learn a model of...
 
Using optical defocus to denoise
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qi Shan, Jiaya Jia, Sing Bing Kang, Zenglu Qin
Issue Date:June 2010
pp. 561-568
Effective reduction of noise is generally difficult because of the possible tight coupling of noise with high-frequency image structure. The problem is worse under low-light conditions. In this paper, we propose slightly optically defocusing the image in o...
 
Generating sharp panoramas from motion-blurred videos
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yunpeng Li, Sing Bing Kang, Neel Joshi, Steve M. Seitz, Daniel P. Huttenlocher
Issue Date:June 2010
pp. 2424-2431
In this paper, we show how to generate a sharp panorama from a set of motion-blurred video frames. Our technique is based on joint global motion estimation and multi-frame deblurring. It also automatically computes the duty cycle of the video, namely the p...
 
Removing rolling shutter wobble
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Simon Baker, Eric Bennett, Sing Bing Kang, Richard Szeliski
Issue Date:June 2010
pp. 2392-2399
We present an algorithm to remove wobble artifacts from a video captured with a rolling shutter camera undergoing large accelerations or jitter. We show how estimating the rapid motion of the camera can be posed as a temporal super-resolution problem. The ...
 
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...
 
Automatic Estimation and Removal of Noise from a Single Image
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ce Liu, Richard Szeliski, Sing Bing Kang, C. Lawrence Zitnick, William T. Freeman
Issue Date:February 2008
pp. 299-314
Image denoising algorithms often assume an additive white Gaussian noise (AWGN) process that is independent of the actual RGB values. Such approaches are not fully automatic and cannot effectively remove color noise produced by today’s CCD digita...
 
Layered Depth Panoramas
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ke Colin Zheng, Sing Bing Kang, Michael F. Cohen, Richard Szeliski
Issue Date:June 2007
pp. 1-8
Representations for interactive photorealistic visualization of scenes range from compact 2D panoramas to data-intensive 4D light fields. In this paper, we propose a technique for creating a layered representation from a sparse set of images taken with a h...
 
Inferring Temporal Order of Images From 3D Structure
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Grant Schindler, Frank Dellaert, Sing Bing Kang
Issue Date:June 2007
pp. 1-7
In this paper, we describe a technique to temporally sort a collection of photos that span many years. By reasoning about persistence of visible structures, we show how this sorting task can be formulated as a constraint satisfaction problem (CSP). Casting...
 
Automatic Removal of Chromatic Aberration from a Single Image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sing Bing Kang
Issue Date:June 2007
pp. 1-8
Many high resolution images exhibit chromatic aberration (CA), where the color channels appear shifted. Unfortunately, merely compensating for these shifts is sometimes inadequate, because the intensities are modified by other effects such as spatially-var...
 
High Resolution Animated Scenes from Stills
Found in: IEEE Transactions on Visualization and Computer Graphics
By Zhouchen Lin, Lifeng Wang, Yunbo Wang, Sing Bing Kang, Tian Fang
Issue Date:May 2007
pp. 562-568
<p><b>Abstract</b>—Current techniques for generating animated scenes involve either videos (whose resolution is limited) or a single image (which requires a significant amount of user interaction). In this paper, we describe a system that...
 
Noise Estimation from a Single Image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ce Liu, William T. Freeman, Richard Szeliski, Sing Bing Kang
Issue Date:June 2006
pp. 901-908
In order to work well, many computer vision algorithms require that their parameters be adjusted according to the image noise level, making it an important quantity to estimate. We show how to estimate an upper bound on the noise level from a single image ...
 
Video Completion by Motion Field Transfer
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Takaaki Shiratori, Yasuyuki Matsushita, Xiaoou Tang, Sing Bing Kang
Issue Date:June 2006
pp. 411-418
Existing methods for video completion typically rely on periodic color transitions, layer extraction, or temporally local motion. However, periodicity may be imperceptible or absent, layer extraction is difficult, and temporally local motion cannot handle ...
 
Multi-View Multi-Exposure Stereo
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Alejandro Troccoli, Sing Bing Kang, Steve Seitz
Issue Date:June 2006
pp. 861-868
Multi-view stereo algorithms typically rely on same-exposure images as inputs due to the brightness constancy assumption. While state-of-the-art depth results are excellent, they do not produce high-dynamic range textures required for high-quality view rec...
 
Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vaibhav Vaish, Marc Levoy, Richard Szeliski, C. L. Zitnick, Sing Bing Kang
Issue Date:June 2006
pp. 2331-2338
Most algorithms for 3D reconstruction from images use cost functions based on SSD, which assume that the surfaces being reconstructed are visible to all cameras. This makes it difficult to reconstruct objects which are partially occluded. Recently, researc...
 
Single-Image Vignetting Correction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yuanjie Zheng, Stephen Lin, Sing Bing Kang
Issue Date:June 2006
pp. 461-468
In this paper, we propose a method for 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 vignetting informa...
 
Stereo Matching with Linear Superposition of Layers
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yanghai Tsin, Sing Bing Kang, Richard Szeliski
Issue Date:February 2006
pp. 290-301
In this paper, we address stereo matching in the presence of a class of non-Lambertian effects, where image formation can be modeled as the additive superposition of layers at different depths. The presence of such effects makes it impossible for tradition...
 
Parameter-Free Radial Distortion Correction with Centre of Distortion Estimation
Found in: Computer Vision, IEEE International Conference on
By Richard I. Hartley, Sing Bing Kang
Issue Date:October 2005
pp. 1834-1841
<p>We propose a method of simultaneously calibrating the radial distortion function of a camera alongwith the other internal calibration parameters. The method relies on the use of a planar (or alternatively non-planar) calibration grid, which is cap...
 
Consistent Segmentation for Optical Flow Estimation
Found in: Computer Vision, IEEE International Conference on
By C. Lawrence Zitnick, Nebojsa Jojic, Sing Bing Kang
Issue Date:October 2005
pp. 1308-1315
In this paper, we propose a method for jointly computing optical flow and segmentating video while accounting for mixed pixels (matting). Our method is based on statistical modeling of an image pair using constraints on appearance and motion. Segments are ...
 
Separating Reflections in Human Iris Images for Illumination Estimation
Found in: Computer Vision, IEEE International Conference on
By Huiqiong Wang, Stephen Lin, Xiaopei Liu, Sing Bing Kang
Issue Date:October 2005
pp. 1691-1698
A method is presented for separating corneal reflections in an image of human irises to estimate illumination from the surrounding scene. Previous techniques for reflection separation have demonstrated success in only limited cases, such as for uniform col...
 
Symmetric Stereo Matching for Occlusion Handling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jian Sun, Yin Li, Sing Bing Kang, Heung-Yeung Shum
Issue Date:June 2005
pp. 399-406
In this paper, we propose a symmetric stereo model to handle occlusion in dense two-frame stereo. Our occlusion reasoning is directly based on the visibility constraint that is more general than both ordering and uniqueness constraints used in previous wor...
 
Boundary Matting for View Synthesis
Found in: Computer Vision and Pattern Recognition Workshop
By Samuel W. Hasinoff, Sing Bing Kang, Richard Szeliski
Issue Date:July 2004
pp. 170
In the last few years, new view synthesis has emerged as an important application of 3D stereo reconstruction. While the quality of stereo has improved, it is still imperfect, and a unique depth is typically assigned to every pixel. This is problematic at ...
 
Image-Based Interactive Exploration of Real-World Environments
Found in: IEEE Computer Graphics and Applications
By Matthew Uyttendaele, Antonio Criminisi, Sing Bing Kang, Simon Winder, Richard Szeliski, Richard Hartley
Issue Date:May 2004
pp. 52-63
This article describes an image-based acquisition and rendering system that enables users to explore remote real-world locations. The system is based on a lightweight, high-resolution, multisensor camera that can be used to quickly film a tour through a la...
 
Error Analysis of Pure Rotation-Based Self-Calibration
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lei Wang, Sing Bing Kang, Heung-Yeung Shum, Guangyou Xu
Issue Date:January 2004
pp. 275-280
<p><b>Abstract</b>—Self-calibration using pure rotation is a well-known technique and has been shown to be a reliable means for recovering intrinsic camera parameters. However, in practice, it is virtually impossible to ensure that the ca...
 
Stereo Matching with Reflections and Translucency
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yanghai Tsin, Sing Bing Kang, Richard Szeliski
Issue Date:June 2003
pp. 702
In this paper, we address the stereo matching problem in the presence of reflections and translucency, where image formation can be modeled as the additive superposition of layers at different depth. The presence of such effects violates the Lambertian ass...
 
Directional Histogram Model for Three-Dimensional Shape Similarity
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xinguo Liu, Robin Sun, Sing Bing Kang, Heung-Yeung Shum
Issue Date:June 2003
pp. 813
In this paper, we propose a novel shape representation we call Directional Histogram Model (DHM). It captures the shape variation of an object and is invariant to scaling and rigid transforms. The DHM is computed by first extracting a directional distribut...
 
Lighting Interpolation by Shadow Morphing Using Intrinsic Lumigraphs
Found in: Computer Graphics and Applications, Pacific Conference on
By Yasuyuki Matsushita, Sing Bing Kang, Stephen Lin, Heung-Yeung Shum, Xin Tong
Issue Date:October 2002
pp. 58
Densely-sampled image representations such as the light field or Lumigraph have been effective in enabling photorealistic image synthesis. Unfortunately, lighting interpolation with such representations has not been shown to be possible without the use of ...
 
Single-Image Reflectance Estimation for Relighting by Iterative Soft Grouping
Found in: Computer Graphics and Applications, Pacific Conference on
By Yuanzhen Li, Stephen Lin, Sing Bing Kang, Hanqing Lu, Heung-Yeung Shum
Issue Date:October 2002
pp. 483
Reflectance values for image-based relighting are often estimated from grouped pixels with similar reflectance, but such groupings are difficult to compute with certainty for sparse image data. To address this problem, we propose an iterative method that a...
 
Multibaseline Stereo in the Presence of Specular Reflections
Found in: Pattern Recognition, International Conference on
By Yuanzhen Li, Stephen Lin, Hanqing Lu, Sing Bing Kang, Heung-Yeung Shum
Issue Date:August 2002
pp. 30573
We address the problem of accurate depth estimation using multibaseline stereo in the presence of specular reflections. Specular reflections can cause the intensity and color of corresponding points to change dramatically according to different viewpoints,...
 
Optimal Texture Map Reconstruction from Multiple Views
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lifeng Wang, Sing Bing Kang, Richard Szeliski, Heung-Yeung Shum
Issue Date:December 2001
pp. 347
The recovery of 3D models from multiple reference images involves not only the extraction of 3D shape, but also of texture. Assuming that all surfaces are Lambertian, the resulting final texture is typically computed as a linear combination of reference te...
 
Handling Occlusions in Dense Multi-view Stereo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sing Bing Kang, Richard Szeliski, Jinxiang Chai
Issue Date:December 2001
pp. 103
While stereo matching was originally formulated as the recovery of 3D shape from a pair of images, it is now generally recognized that using more than two images can dramatically improve the quality of the reconstruction. Unfortunately, as more images are ...
 
Error Analysis of Pure Rotation-based Self-Calibration
Found in: Computer Vision, IEEE International Conference on
By Lei Wang, Sing Bing Kang, Heung-Yeung Shum, Guangyou Xu
Issue Date:July 2001
pp. 464
Self-calibration using pure rotation is a well-known technique, and has been shown to be a reliable means for recovering intrinsic camera parameters. However, in practice, it is virtually impossible to ensure that the camera motion for this type of self-ca...
 
Combined Spline- and Block-Based Motion Estimation for Video Coding
Found in: Pattern Recognition, International Conference on
By Frédéric Dufaux, Sing Bing Kang
Issue Date:September 2000
pp. 3071
In this paper, we propose a new, efficient, and fast technique to estimate motion for video coding. Our technique combines spline-based registration and block matching motion estimation. It replaces the initial compute-intensive gross block-matching search...
 
Catadioptric Self-Calibration
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sing Bing Kang
Issue Date:June 2000
pp. 1201
We have assembled a standalone, movable system that can capture long sequences of omni-directional images (up to 1,500 images at 6.7 Hz and a resolution of 1140 ? 1030). The goal of this system is to reconstruct complex large environments, such as an entir...
 
 1  2 Next >>