Search For:

Displaying 1-21 out of 21 total
Radiometric Calibration from a Single Image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stephen Lin, Jinwei Gu, Shuntaro Yamazaki, Heung-Yeung Shum
Issue Date:July 2004
pp. 938-945
Photometric methods in computer vision require calibration of the camera?s radiometric response, and previous works have addressed this problem using multiple registered images captured under different camera exposure settings. In many instances, such an i...
 
Compressive Structured Light for Recovering Inhomogeneous Participating Media
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jinwei Gu,S. K. Nayar,E. Grinspun,P. N. Belhumeur,R. Ramamoorthi
Issue Date:March 2013
pp. 1
We propose a new method named compressive structured light for recovering inhomogeneous participating media. Whereas conventional structured light methods emit coded light patterns onto the surface of an opaque object to establish correspondence for triang...
 
What is the space of spectral sensitivity functions for digital color cameras?
Found in: 2013 IEEE Workshop on Applications of Computer Vision (WACV)
By Jun Jiang,Dengyu Liu,Jinwei Gu,Sabine Susstrunk
Issue Date:January 2013
pp. 168-179
Camera spectral sensitivity functions relate scene radiance with captured RGB triplets. They are important for many computer vision tasks that use color information, such as multispectral imaging, color rendering, and color constancy. In this paper, we aim...
 
Discriminative illumination: Per-pixel classification of raw materials based on optimal projections of spectral BRDF
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jinwei Gu, Chao Liu
Issue Date:June 2012
pp. 797-804
Classifying raw, unpainted materials - metal, plastic, ceramic, fabric, etc. - is an important yet challenging task for computer vision. Previous works measure subsets of surface spectral reflectance as features for classification. However, acquiring the f...
 
Multiplexed illumination for scene recovery in the presence of global illumination
Found in: Computer Vision, IEEE International Conference on
By Jinwei Gu,Toshihiro Kobayashi,Mohit Gupta,Shree K. Nayar
Issue Date:November 2011
pp. 691-698
Global illumination effects such as inter-reflections and subsurface scattering result in systematic, and often significant errors in scene recovery using active illumination. Recently, it was shown that the direct and global components could be separated ...
 
Video from a single coded exposure photograph using a learned over-complete dictionary
Found in: Computer Vision, IEEE International Conference on
By Yasunobu Hitomi,Jinwei Gu,Mohit Gupta,Tomoo Mitsunaga,Shree K. Nayar
Issue Date:November 2011
pp. 287-294
Cameras face a fundamental tradeoff between the spatial and temporal resolution - digital still cameras can capture images with high spatial resolution, but most high-speed video cameras suffer from low spatial resolution. It is hard to overcome this trade...
 
A Novel Algorithm for Detecting Singular Points from Fingerprint Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jie Zhou, Fanglin Chen, Jinwei Gu
Issue Date:July 2009
pp. 1239-1250
Fingerprint analysis is typically based on the location and pattern of detected singular points in the images. These singular points (cores and deltas) not only represent the characteristics of local ridge patterns but also determine the topological struct...
 
A Novel Model for Orientation Field of Fingerprints
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jinwei Gu, Jie Zhou
Issue Date:June 2003
pp. 493
As a global feature of fingerprint, orientation field is very important to automatic fingerprint identification system (AFIS). Establishing an accurate and concise model for orientation field will not only improve the performance of orientation estimation,...
 
Removing image artifacts due to dirty camera lenses and thin occluders
Found in: ACM Transactions on Graphics (TOG)
By Jinwei Gu, Peter Belhumeur, Ravi Ramamoorthi, Shree Nayar, Jinwei Gu, Peter Belhumeur, Ravi Ramamoorthi, Shree Nayar
Issue Date:December 2009
pp. 1-2
Dirt on camera lenses, and occlusions from thin objects such as fences, are two important types of artifacts in digital imaging systems. These artifacts are not only an annoyance for photographers, but also a hindrance to computer vision and digital forens...
     
Printing spatially-varying reflectance
Found in: ACM Transactions on Graphics (TOG)
By Boris Ajdin, Fabio Pellacini, Hendrik P. A. Lensch, Jason Lawrence, Jinwei Gu, Szymon Rusinkiewicz, Wojciech Matusik, Boris Ajdin, Fabio Pellacini, Hendrik P. A. Lensch, Jason Lawrence, Jinwei Gu, Szymon Rusinkiewicz, Wojciech Matusik
Issue Date:December 2009
pp. 1-2
Although real-world surfaces can exhibit significant variation in materials --- glossy, diffuse, metallic, etc. --- printers are usually used to reproduce color or gray-scale images. We propose a complete system that uses appropriate inks and foils to prin...
     
Efficient Space-Time Sampling with Pixel-Wise Coded Exposure for High-Speed Imaging
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Dengyu Liu, Jinwei Gu,Yasunobu Hitomi,Mohit Gupta,Tomoo Mitsunaga,Shree K. Nayar
Issue Date:February 2014
pp. 248-260
Cameras face a fundamental trade-off between spatial and temporal resolution. Digital still cameras can capture images with high spatial resolution, but most high-speed video cameras have relatively low spatial resolution. It is hard to overcome this trade...
 
Discriminative Illumination: Per-Pixel Classification of Raw Materials Based on Optimal Projections of Spectral BRDF
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chao Liu, Jinwei Gu
Issue Date:January 2014
pp. 86-98
Classifying raw, unpainted materials--metal, plastic, ceramic, fabric, and so on--is an important yet challenging task for computer vision. Previous works measure subsets of surface spectral reflectance as features for classification. However, acquiring th...
 
Learning Discriminative Illumination and Filters for Raw Material Classification with Optimal Projections of Bidirectional Texture Functions
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Chao Liu,Geifei Yang,Jinwei Gu
Issue Date:June 2013
pp. 1430-1437
We present a computational imaging method for raw material classification using features of Bidirectional Texture Functions (BTF). Texture is an intrinsic feature for many materials, such as wood, fabric, and granite. At appropriate scales, even "unif...
 
An improved quantum genetic algorithm for stochastic job shop problem
Found in: Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC '09)
By Bin Jiao, Cuiwen Cao, Jinwei Gu, Xingsheng Gu
Issue Date:June 2009
pp. 70-73
This paper considers the stochastic job shop scheduling problem with the objective of minimizing the expected value of makespan and the processing times of jobs being subject to independent normal distributions. In order to solve this problem, we devise an...
     
Research on job shop scheduling under uncertainty
Found in: Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC '09)
By Bin Jiao, Jinwei Gu, Xingsheng Gu, Zhenhao Xu
Issue Date:June 2009
pp. 70-73
In many real world applications, the processing time of products in Job Shop scheduling problems is not a fixed value, and may vary dynamically with the situation. In this study, the scheduling mathematical model of Job Shop problems with uncertain process...
     
An improved quantum genetic algorithm for stochastic flexible scheduling problem with breakdown
Found in: Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC '09)
By Bin Jiao, Cuiwen Cao, Jinwei Gu, Xingsheng Gu
Issue Date:June 2009
pp. 70-73
A stochastic flexible scheduling problem subject to random breakdowns is studied in this paper, which objective is to minimize the expected value of makespan. We consider a preemptive-resume model of breakdown. The processing times, breakdown intervals and...
     
Optimizing constrained non-convex NLP problems in chemical engineering field by a novel modified goal programming genetic algorithm
Found in: Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation (GEC '09)
By Bin Jiao, Cuiwen Cao, Jinwei Gu, Xingsheng Gu, Zhong Xin
Issue Date:June 2009
pp. 70-73
A novel modified goal programming genetic algorithm (MGPGA) is presented in this paper to solve constrained non-convex nonlinear programming (NLP) problems. This new method eliminates the complex equality constraints from original model and transforms them...
     
Removing image artifacts due to dirty camera lenses and thin occluders
Found in: ACM SIGGRAPH Asia 2009 papers (SIGGRAPH Asia '09)
By Jinwei Gu, Peter Belhumeur, Ravi Ramamoorthi, Shree Nayar
Issue Date:December 2009
pp. 1-6
Dirt on camera lenses, and occlusions from thin objects such as fences, are two important types of artifacts in digital imaging systems. These artifacts are not only an annoyance for photographers, but also a hindrance to computer vision and digital forens...
     
Printing spatially-varying reflectance
Found in: ACM SIGGRAPH Asia 2009 papers (SIGGRAPH Asia '09)
By Boris Ajdin, Fabio Pellacini, Hendrik P. A. Lensch, Jason Lawrence, Jinwei Gu, Szymon Rusinkiewicz, Wojciech Matusik
Issue Date:December 2009
pp. 1-6
Although real-world surfaces can exhibit significant variation in materials --- glossy, diffuse, metallic, etc. --- printers are usually used to reproduce color or gray-scale images. We propose a complete system that uses appropriate inks and foils to prin...
     
Time-varying surface appearance: acquisition, modeling and rendering: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: ACM SIGGRAPH 2006 Papers (SIGGRAPH '06)
By Chien-I Tu, Jinwei Gu, Peter Belhumeur, Ravi Ramamoorthi, Shree Nayar, Wojciech Matusik
Issue Date:July 2006
pp. 33-es
For computer graphics rendering, we generally assume that the appearance of surfaces remains static over time. Yet, there are a number of natural processes that cause surface appearance to vary dramatically, such as burning of wood, wetting and drying of r...
     
Time-varying surface appearance: acquisition, modeling and rendering: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Chien-I Tu, Jinwei Gu, Peter Belhumeur, Ravi Ramamoorthi, Shree Nayar, Wojciech Matusik
Issue Date:July 2006
pp. 33-es
For computer graphics rendering, we generally assume that the appearance of surfaces remains static over time. Yet, there are a number of natural processes that cause surface appearance to vary dramatically, such as burning of wood, wetting and drying of r...
     
 1