A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Resolution Limits of Sparse Coding in High Dimensions
2008
Neural Information Processing Systems
The main results in this paper are necessary and sufficient conditions for asymptotically-reliable sparsity pattern recovery in terms of the dimensions m, n and k as well as the signal-tonoise ratio (SNR ...
This provides insight on the precise value and limitations of convex programming-based algorithms. ...
The high SNR limit (13) matches the sufficient condition in [24] for the noise free case, except that the constant in ( 13 ) is tighter.
Numerical validation. ...
dblp:conf/nips/FletcherRG08
fatcat:a2k6gsrrjjfthosc3krdisozf4
Real-Time Video Scaling Based On Convolution Neural Network Architecture
2017
Indonesian Journal of Electrical Engineering and Computer Science
quality while scaling of large datasets from lower resolution frames to high resolution frames. ...
In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. ...
In this paper author faces problem of ill posed in reconstruction of high dimension super resolution image and training of large datasets is also a vital issue. ...
doi:10.11591/ijeecs.v7.i2.pp381-394
fatcat:fvqcahgpqjh6dd2j27rrokckti
Performance improvement in multi-ship imaging for ScanSAR based on sparse representation
2012
Science China Information Sciences
In [8], a super-resolution technique is proposed to improve cross-range resolution by exploiting the sparseness of ISAR imagery, wherein resolution enhancement is realized from limited pulses. ...
In addition, from the viewpoint that a multi-ship target is composed of only a limited number of strong scatterers, it is sparse in the SAR image domain. ...
Hence, Chirp coding in one dimension is considered a good choice in sparse Bayesian SAR imaging. ...
doi:10.1007/s11432-012-4626-3
fatcat:aymqg47umvh5ncnj4upo37lskq
TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
[article]
2019
arXiv
pre-print
Secondly, we propose TGAN that integrates deep convolutional generative adversarial networks and tensor super-resolution in a cascading manner, to generate high-quality images from random distributions ...
Essentially, the adversarial process of TGAN takes place in a tensor space. ...
We have tensor product relationships in tensor sparse coding: T h = D h * C h and T l = D l * C l , where C h , C l denotes tensor sparse coefficients for high-resolution images and low-resolution images ...
arXiv:1901.09953v2
fatcat:qxecq5meorhotpcpaamnt2n5ha
Video from a single coded exposure photograph using a learned over-complete dictionary
2011
2011 International Conference on Computer Vision
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 ...
Using both simulations and experiments on a wide range of scenes, we show that our method can effectively reconstruct a video from a single image maintaining high spatial resolution. ...
Acknowledgments: This research was supported in parts by Sony Corporation, NSF (grant number IIS 09-64429) and ONR (grant number N00014-08-1-0638). ...
doi:10.1109/iccv.2011.6126254
dblp:conf/iccv/HitomiGGMN11
fatcat:fyn3lox5mfc75bkmjor2aq75ki
Convolutional Sparse Coding for Capturing High-Speed Video Content
2017
Computer graphics forum (Print)
Video capture is limited by the trade-off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the ...
The recent introduction of compressive sensing and sparse reconstruction techniques allows for the capture of single-shot high-speed video, by coding the temporal information in a single frame, and then ...
camera and some of the videos used in this paper. ...
doi:10.1111/cgf.13086
fatcat:pmbhmoixibfqpf4nnfg6eaua7m
Tensor Super-Resolution with Generative Adversarial Nets: A Large Image Generation Approach
[chapter]
2019
Communications in Computer and Information Science
In this paper, we propose a novel scheme using tensor super-resolution with adversarial generative nets (TSRGAN), to generate large high-quality images by exploring tensor structures. ...
Secondly, we propose TSRGAN that integrates deep convolutional generative adversarial networks and tensor super-resolution in a cascading manner, to generate high-quality images from random distributions ...
We have tensor product relationships in tensor sparse coding: T h = D h * C h and T l = D l * C l , where C h , C l denotes tensor sparse coefficients for high-resolution images and low-resolution images ...
doi:10.1007/978-981-15-1398-5_15
fatcat:jtt7owp4drdmzfceowda5336ie
Dual-coded compressive hyperspectral imaging
2014
Optics Letters
high-resolution signal can be recovered in postprocessing. ...
We demonstrate that two high-speed spatial light modulators, located conjugate to the image and spectral plane, respectively, can code the hyperspectral datacube into a single sensor image such that the ...
This work was supported by the Project of NSFC (Nos. 61327902, 61120106003, and 61035002). Gordon Wetzstein was supported by the NSERC PDF. ...
doi:10.1364/ol.39.002044
pmid:24686670
fatcat:gdfk2qikpjcflbuj5ag3xh3y7e
REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE
2017
ICTACT Journal on Image and Video Processing
quality while scaling of large datasets from lower resolution frames to high resolution frames. ...
In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. ...
36] [37] consists of some limitations related to its high resolution and image reconstruction when upscaling factor increases. ...
doi:10.21917/ijivp.2017.0218
fatcat:wajl26qdz5bepfcuzynhvuhahq
Image Transformation Based on Learning Dictionaries across Image Spaces
2013
IEEE Transactions on Pattern Analysis and Machine Intelligence
The contributions of our proposed framework are three-fold. (1) We propose a concept of coupled dictionary learning based on coupled sparse coding, which requires the sparse coefficient vectors of a pair ...
of corresponding source and target image patches have the same support, i.e., the same indices of nonzero elements. (2) We devise a space partitioning scheme to divide the high-dimensional but sparse ...
[15] used sparse coding for super-resolution, which enforces corresponding low-and high-resolution image patches to share the same sparse feature values. ...
doi:10.1109/tpami.2012.95
pmid:22529324
fatcat:b26jvrj4w5g3tpt2ayqpru4nru
Bayesian sparse representation for hyperspectral image super resolution
2015
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
The distributions are then used to compute sparse codes of the high resolution image. ...
Despite the proven efficacy of hyperspectral imaging in many computer vision tasks, its widespread use is hindered by its low spatial resolution, resulting from hardware limitations. ...
Later, this information is used to sparse code a high resolution image (e.g. RGB) of the same scene. ...
doi:10.1109/cvpr.2015.7298986
dblp:conf/cvpr/AkhtarSM15
fatcat:36776a2h6nfibj7vdtl3h2wh5i
Towards Motion Aware Light Field Video for Dynamic Scenes
2013
2013 IEEE International Conference on Computer Vision
Our reconstruction is motion-aware and offers a continuum of resolution tradeoff with increasing motion in the scene. ...
Current Light Field (LF) cameras offer fixed resolution in space, time and angle which is decided a-priori and is independent of the scene. ...
Coded Aperture: Coded aperture imaging has been widely used in astronomy [28] to overcome the limitations imposed by a pinhole camera. ...
doi:10.1109/iccv.2013.129
dblp:conf/iccv/TambeVA13
fatcat:ucib636dbnej5ko452pjgvm7vu
Compression and Real-Time Rendering of Inward Looking Spherical Light Fields
2020
Annual Conference of the European Association for Computer Graphics
There are various ways to acquire light fields depending on the nature of the scene, limitations on the capturing setup, and the application at hand. ...
Our focus in this paper is on full-parallax imaging of large-scale static objects for photorealistic real-time rendering. ...
[MSOC * 19] proposed a user-guided capturing system for inward-looking light fields, but it has limitations on capturing light fields with high spatial resolution. ...
doi:10.2312/egs.20201007
dblp:conf/eurographics/HajisharifMBLU20
fatcat:lfftdqcqjvgbjaukqg4s3juthu
Quantitative characterization of super-resolution infrared imaging based on time-varying focal plane coding
2014
Journal of the European Optical Society-Rapid Publications
High resolution infrared image has been the goal of an infrared imaging system. ...
In this paper, a super-resolution infrared imaging method using time-varying coded mask is proposed based on focal plane coding and compressed sensing theory. ...
ACKNOWLEDGEMENTS This research is supported by the National Natural Science Foundation of China (61007014, 61377007). We express our sincere appreciation for reviewers valuable comments. ...
doi:10.2971/jeos.2014.14043
fatcat:u4gemohmzjgyzneesuo6gifjvm
HSCNN: CNN-Based Hyperspectral Image Recovery from Spectrally Undersampled Projections
2017
2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
These measurements are first upsampled in the spectral dimension through simple interpolation or CS reconstruction, and the proposed method learns an end-to-end mapping from a large number of upsampled ...
We explore different network configurations to achieve high reconstruction fidelity. ...
of a 2D image, yet here the resolution is enhanced in the spectral dimension. ...
doi:10.1109/iccvw.2017.68
dblp:conf/iccvw/XiongSLWLW17
fatcat:xqotf7er3zaa3kd6ildao3xlpe
« Previous
Showing results 1 — 15 out of 79,004 results