Filters








8,463 Hits in 7.1 sec

Continuous digital zooming using generative adversarial networks for dual camera system

Yifan Yang, Qi Li, Yongyi Yu, Zhuang He, Huajun Feng, Zhihai Xu, Yueting Chen
2021 IET Image Processing  
In dual camera system, shorter focal length module produces the wide-view image with the low resolution.  ...  Firstly, a feature extraction block (FEB) is advanced to extract feature of long-focal image and short focal-image to reconstruct a wide-view image with different resolutions.  ...  Therefore, images of different resolutions are acquired in the dual FIGURE 1 Dual camera system camera system.  ... 
doi:10.1049/ipr2.12274 fatcat:w45brilhgjgbjfuouaraahbykm

High-Quality Multi-View Image Extraction from a Light Field Camera Considering Its Physical Pixel Arrangement

Shu FUJITA, Keita TAKAHASHI, Toshiaki FUJII
2019 IEICE transactions on information and systems  
Moreover, we also mention another type of light field cameras, a Raytrix camera, and describe how it can be handled to extract high-quality multi-view images. key words: light field camera, super resolution  ...  We use a Lytro Illum camera to obtain 4D light field data (a set of multi-viewpoint images) through a micro-lens array.  ...  Estimating the Depth Map The basic principle for depth estimation is the same as multi-view stereo based on block matching.  ... 
doi:10.1587/transinf.2018awi0004 fatcat:hre62wzrlnd53j2qoo5b5cr4yq

Trends in Super-High-Definition Imaging Techniques Based on Deep Neural Networks

Hyung-Il Kim, Seok Bong Yoo
2020 Mathematics  
In this review article, we investigate the current state-of-the-art super-high-definition imaging techniques in terms of image denoising for removing the compressed Poisson noises as well as super-resolution  ...  Images captured by cameras in closed-circuit televisions and black boxes in cities have low or poor quality owing to lens distortion and optical blur.  ...  network for the super-resolution of a multi-directional input patch with low directivity (LD).  ... 
doi:10.3390/math8111907 fatcat:du52r6z5nneh5lmwbtmacbr5jm

High-resolution image reconstruction from multiple differently exposed images

B.K. Gunturk, M. Gevrekci
2006 IEEE Signal Processing Letters  
In this letter, we propose a Bayesian super-resolution algorithm based on an imaging model that includes camera response function, exposure time, sensor noise, and quantization error in addition to spatial  ...  Super-resolution reconstruction is the process of reconstructing a high-resolution image from multiple low-resolution images.  ...  Such a multi-frame resolution enhancement process is referred to as super-resolution reconstruction in the literature [1] .  ... 
doi:10.1109/lsp.2005.863693 fatcat:2ywfqmwrmnek7cbihlsx6mlvpy

Super-resolution of a 3-dimensional scene from novel viewpoints

Kyle Nelson, Asim Bhatti, Saeid Nahavandi
2012 2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)  
Drawing on ideas from super-resolution and multi-view geometry this thesis has developed a complete 3D super-resolution pipeline including intelligent frame selection, optimal viewpoint selection and robust  ...  Multi-frame super-resolution algorithms require several slightly different perspectives of the same scene, a non-integer pixel shift between images, such that each input view captures a marginally different  ...  Chapter 5 presents a novel technique for intelligently finding the optimal viewpoint of a scene, which is applied here to multi-view super-resolution.  ... 
doi:10.1109/icarcv.2012.6485347 dblp:conf/icarcv/NelsonBN12 fatcat:wfakbldhzfhl3jlkcwsuu7v34m

Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning [article]

Marc Bosch and Christopher M. Gifford and Pedro A. Rodriguez
2017 arXiv   pre-print
We propose a GAN-based architecture using densely connected convolutional neural networks (DenseNets) to be able to super-resolve overhead imagery with a factor of up to 8x.  ...  Recent advances in Generative Adversarial Learning allow for new modalities of image super-resolution by learning low to high resolution mappings.  ...  Figure 1 . 1 Super-resolution applied to overhead imagery using our system. Figure 2 . 2 Generator architecture for overhead imagery.  ... 
arXiv:1711.10312v1 fatcat:6pl6vuwkvvgnxafjiqxp7ia5s4

A Coarse Elevation Map-based Registration Method for Super-resolution of Three-line Scanner Images

Rongjun Qin, Jianya Gong, Hongli Li, Xianfeng Huang
2013 Photogrammetric Engineering and Remote Sensing  
In terms of super-resolution, we also propose a tree-based fast adaptive template matching method for Knife-edge detection to fully automate the SRKE super-resolution algorithm.  ...  Multi-frame SR however, encounters an inevitable problem in that there must be a pixel-to-pixel match among the low-resolution (LR) images, or image registration.  ...  Due to the number of original images available, super-resolution methods can be divided into two scenarios: Multi-frame super-resolution and Single motivated us to start the registration in similar but  ... 
doi:10.14358/pers.79.8.717 fatcat:xpkn5dmpdvcg7jalo2drwdtrma

A Video Super-Resolution Framework Using SCoBeP

Nafise Barzigar, Aminmohammad Roozgard, Pramode Verma, Samuel Cheng
2016 IEEE transactions on circuits and systems for video technology (Print)  
This paper presents new approaches to video super resolution, based on sparse coding and belief propagation.  ...  In addition, the experimental results show that our models are naturally robust in handling super resolution on video sequences affected by scene motions and/or small camera motions.  ...  ACKNOWLEDGMENT The authors would like to thank the associate editor and the anonymous reviewers for their constructive comments and suggestions. We would also like to thank Mrs.  ... 
doi:10.1109/tcsvt.2013.2283108 fatcat:mkbsx3u7lbcgfowqq7la476yqu

Motion block based video super resolution

Sara Izadpanahi, Hasan Demirel
2013 Digital signal processing (Print)  
A multi-frame super resolution process can be used for enhancing the resolution of video frames by employing the information of consecutive low-resolution frames taken from almost the same scene.  ...  The proposed motionblock based super resolution method not only offers a local motion model but also deals with the occluded areas in a proper way.  ...  In addition, reducing the size of blocks in super resolving images, allows the system to function faster.  ... 
doi:10.1016/j.dsp.2013.04.002 fatcat:d574qf4ecvcplkrajoz4hs7z6m

Exploiting Raw Images for Real-Scene Super-Resolution [article]

Xiangyu Xu, Yongrui Ma, Wenxiu Sun, Ming-Hsuan Yang
2021 arXiv   pre-print
Super-resolution is a fundamental problem in computer vision which aims to overcome the spatial limitation of camera sensors.  ...  To address the first issue, we propose a method to generate more realistic training data by mimicking the imaging process of digital cameras.  ...  Thus, it is often desirable to capture the wide-range scene at a lower resolution with a short-focus camera (e.g., a wide-angle lens), and then apply a single image super-resolution algorithm to recover  ... 
arXiv:2102.01579v1 fatcat:tzanyrixcjb6dahh4dxdovancu

Quanta Burst Photography [article]

Sizhuo Ma, Shantanu Gupta, Arin C. Ulku, Claudio Bruschini, Edoardo Charbon, Mohit Gupta
2020 arXiv   pre-print
While these sensors were limited to single-pixel or low-resolution devices in the past, recently, large (up to 1 MPixel) SPAD arrays have been developed.  ...  We demonstrate, via a recently developed SPAD array, that the proposed method is able to generate high-quality images for scenes with challenging lighting, complex geometries, high dynamic range and moving  ...  Using small block sizes. Compared to original-resolution merging, super-resolution merging requires a larger number of blocks (smaller block size).  ... 
arXiv:2006.11840v1 fatcat:phnzzcpugvc5dm55yr5zjdz4ca

Spectral DiffuserCam: lensless snapshot hyperspectral imaging with a spectral filter array [article]

Kristina Monakhova, Kyrollos Yanny, Neerja Aggarwal, Laura Waller
2020 arXiv   accepted
By solving a sparsity-constrained inverse problem, we recover the hyperspectral volume with sub-super-pixel resolution.  ...  Our system consists of a tiled spectral filter array placed directly on the image sensor and a diffuser placed close to the sensor.  ...  ACKNOWLEDGMENTS The authors would like to thank Viavi Solutions (Santa Rosa, CA), and particularly Bill Houck, for their technical help and support, as well as Nick Antipa and Grace Kuo for helpful discussions  ... 
arXiv:2006.08565v2 fatcat:d4llzjdxubeozela65acn7n5oa

MULTI-SCALE COMPRESSED SENSING BASED ON SPLIT AUGMENTED LAGRANGIAN SHRINKAGE ALGORITHM FOR IMAGE SUPER-RESOLUTION RECONSTRUCTION

Tian Shu-yao, Hu Chun-hai
2016 International Journal on Smart Sensing and Intelligent Systems  
And inverse measurement matrix is modified by the upsampling operator to enhance the resolution of image.  ...  This paper proposes a multi-scale compressed sensing algorithm in shearlet domain by exploiting discrete Shearlet transform which can optimally represent the images with edges.  ...  To overcome the above problems, by introducing the idea of single image super resolution [6] , we designed a multi-scale compressed sensing in Shearlet-domainbased image super resolution fast reconstruction  ... 
doi:10.21307/ijssis-2017-884 fatcat:uz3zglolbraazggmnsg2tqm75a

Super-resolution still and video reconstruction from MPEG-coded video

Y. Altunbasak, A.J. Patti, R.M. Mersereau
2002 IEEE transactions on circuits and systems for video technology (Print)  
Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden to  ...  Public reporting burden for ttiis colleclion of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching data sources, gathering and maintaining  ...  All these systems propose super-resolution as a separate preprocessing block in front of a face recognition system.  ... 
doi:10.1109/76.999200 fatcat:7k2ksmuacbdxhl747iotzyc7pi

Block-matching subpixel motion estimation from noisy undersampled frames: an empirical performance evaluation

Sean Borman, Mark A. Robertson, Robert L. Stevenson, Kiyoharu Aizawa, Robert L. Stevenson, Ya-Qin Zhang
1998 Visual Communications and Image Processing '99  
This study is motivated by the requirement for reliable subpixel accuracy motion estimates for motion compensated observation models used in multi-frame super-resolution image reconstruction.  ...  The performance of block-matching sub-pixel motion estimation algorithms under the adverse conditions of image undersampling and additive noise is studied empirically.  ...  Block-matching sub-pixel motion estimation techniques are applied to the simulated camera imagery resulting in motion estimates which can be compared with the a-priori known motion.  ... 
doi:10.1117/12.334654 fatcat:rgubjazy6fbj7a7ulqb5634a3a
« Previous Showing results 1 — 15 out of 8,463 results