Filters








297 Hits in 4.1 sec

Postprocessing of Compressed Images via Sequential Denoising

Yehuda Dar, Alfred M. Bruckstein, Michael Elad, Raja Giryes
2016 IEEE Transactions on Image Processing  
Our approach is based on posing this task as an inverse problem, with a regularization that leverages on existing state-of-the-art image denoising algorithms.  ...  In this work we propose a novel postprocessing technique for compression-artifact reduction.  ...  Our experiments included postprocessing of images compressed using JPEG2000 compression without any tiling.  ... 
doi:10.1109/tip.2016.2558825 pmid:27214878 fatcat:ybzimvw6ezhszhraafx6iqbbaq

Optical architectures for compressive imaging

Mark A. Neifeld, Jun Ke
2007 Applied Optics  
We compare three optical architectures for compressive imaging: sequential, parallel, and photon sharing.  ...  Using a linear reconstruction operator we find that in all cases of (a) there is a measurement noise level above which compressive imaging is superior to conventional imaging.  ...  Within the compressive imaging framework therefore, the imaging system task must define the type and number of projections to be measured as well as the necessary postprocessing.  ... 
doi:10.1364/ao.46.005293 pmid:17676143 fatcat:tesyx4mqznaa3j474f67do2ium

3D denoised completion network for deep single-pixel reconstruction of hyperspectral images

Valeriya Pronina, Antonio Lorente Mur, Juan F. P. J. Abascal, Françoise Peyrin, Dmitry V. Dylov, Nicolas Ducros
2021 Optics Express  
Combined with a spectral detector, the concept of single-pixel imaging allows for hyperspectral imaging.  ...  In particular, we introduce a denoised completion network that includes 3D convolution filters.  ...  The authors declare that they have no conflicts of interest. Data availability. Data underlying the results presented in this paper are available in Refs. [35, 43] .  ... 
doi:10.1364/oe.443134 pmid:34809318 fatcat:fo6emuxbcbcmbbqiunbvrq5pty

Nonconvex compressive video sensing

Liangliang Chen, Ming Yan, Chunqi Qian, Ning Xi, Zhanxin Zhou, Yongliang Yang, Bo Song, Lixin Dong
2016 Journal of Electronic Imaging (JEI)  
Then, an edge-detection-based denoising method is employed to reduce the error in the frame difference image.  ...  The experimental results show that the proposed algorithm together with the single-pixel imaging system makes compressive video cameras available.  ...  Figure 7 (c) shows the performance of this postprocessing (denoising) procedure. The flow chart for this procedure is described in Fig. 8 .  ... 
doi:10.1117/1.jei.25.6.063003 pmid:29622898 pmcid:PMC5881933 fatcat:xr7bedg3ynb5rgnwha5yd5o2a4

Single-pixel Salient Object Detection via Discrete Cosine Spectrum Acquisition and Deep Learning

Yonghao Li, Jianhong Shi, Lei Sun, Xiaoyan Wu, Guihua Zeng
2020 IEEE Photonics Technology Letters  
Single-pixel imaging (SPI) can reduce the cost and have the potential of being competent for some challenging tasks.  ...  Therefore, in this letter, we explore the implement of salient object detection based on SPI system and present a scheme via discrete cosine spectrum (DCS) acquisition and deep learning model.  ...  INTRODUCTION A S A computational imaging system, SPI can break through the limit of hardware by powerful data postprocessing [1] .  ... 
doi:10.1109/lpt.2020.3026472 fatcat:prtzyidgxbdebg6glaa6e7gte4

Denoising of image patches via sparse representations with learned statistical dependencies

Tomer Faktor, Yonina C. Eldar, Michael Elad
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We address the problem of denoising for image patches. The approach taken is based on Bayesian modeling of sparse representations, which takes into account dependencies between the dictionary atoms.  ...  We compare the denoising performance to that of previous sparse recovery methods, which do not exploit the statistical dependencies, and show the effectiveness of our approach.  ...  As for denoising via OMP, it consists of one iteration where we apply the OMP algorithm using the unitary DCT dictionary.  ... 
doi:10.1109/icassp.2011.5947684 dblp:conf/icassp/FaktorEE11 fatcat:pbhgbthtfjaghpe73ae2vuvf24

Denoising sparse images from GRAPPA using the nullspace method

Daniel S. Weller, Jonathan R. Polimeni, Leo Grady, Lawrence L. Wald, Elfar Adalsteinsson, Vivek K. Goyal
2011 Magnetic Resonance in Medicine  
, the DEnoising of Sparse Images from GRAPPA using the Nullspace method is developed.  ...  Several brain images reconstructed from uniformly undersampled k-space data using DEnoising of Sparse Images from GRAPPA using the Nullspace method are compared against reconstructions using existing methods  ...  nevertheless, can improve image quality in the uniformly undersampled case via denoising.  ... 
doi:10.1002/mrm.24116 pmid:22213069 pmcid:PMC3323741 fatcat:vr2q3lmc4zhgbecyg6mrjfj25m

Compressed Sensing via Universal Denoising and Approximate Message Passing [article]

Yanting Ma, Junan Zhu, Dror Baron
2014 arXiv   pre-print
We study compressed sensing (CS) signal reconstruction problems where an input signal is measured via matrix multiplication under additive white Gaussian noise.  ...  Our universal CS recovery algorithm compares favorably with existing reconstruction algorithms in terms of both reconstruction quality and runtime, despite not knowing the input statistics of the stationary  ...  A compressive imaging algorithm that applies non-separable image denoisers within AMP appears in Tan et al. [28] .  ... 
arXiv:1407.1944v2 fatcat:3skzhkcpsrcyhlp3uriink4uue

Second order total generalized variation (TGV) for MRI

Florian Knoll, Kristian Bredies, Thomas Pock, Rudolf Stollberger
2010 Magnetic Resonance in Medicine  
Two important applications are considered in this paper, image denoising and image reconstruction from undersampled radial data sets with multiple coils.  ...  The assumption of TV is that images consist of areas, which are piecewise constant.  ...  While this means that TGV currently can only be used in applications where offline image reconstruction or postprocessing is acceptable, this is the case for many iterative TV or compressed sensing methods  ... 
doi:10.1002/mrm.22595 pmid:21264937 pmcid:PMC4011128 fatcat:askykfgapberzpnigxysb6qb54

Dual-coded compressive hyperspectral imaging

Xing Lin, Gordon Wetzstein, Yebin Liu, Qionghai Dai
2014 Optics Letters  
This Letter presents a new snapshot approach to hyperspectral imaging via dual-optical coding and compressive computational reconstruction.  ...  high-resolution signal can be recovered in postprocessing.  ...  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

Connecting Image Denoising and High-Level Vision Tasks via Deep Learning [article]

Ding Liu, Bihan Wen, Jianbo Jiao, Xianming Liu, Zhangyang Wang, Thomas S. Huang
2018 arXiv   pre-print
Extensive experiments demonstrate the benefit of exploiting image semantics simultaneously for image denoising and high-level vision tasks via deep learning.  ...  Image denoising and high-level vision tasks are usually handled independently in the conventional practice of computer vision, and their connection is fragile.  ...  We show that the cascaded network trained with the joint loss not only boosts the perceptual quality of denoised images via image semantic guidance, but also substantially improves the accuracy of high-level  ... 
arXiv:1809.01826v1 fatcat:fikd6rjy6zai7fekuktwlp2k3e

Accelerated high-resolution photoacoustic tomography via compressed sensing

Simon Arridge, Paul Beard, Marta Betcke, Ben Cox, Nam Huynh, Felix Lucka, Olumide Ogunlade, Edward Zhang
2016 Physics in Medicine and Biology  
Then, we discuss how to implement them using the FP scanner and demonstrate the potential of these novel compressed sensing PAT devices through simulated data from a realistic numerical phantom and through  ...  A particular example is the planar Fabry-Perot (FP) scanner, which yields high-resolution images but takes several minutes to sequentially map the photoacoustic field on the sensor plane, point-by-point  ...  Acknowledgments We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.  ... 
doi:10.1088/1361-6560/61/24/8908 pmid:27910824 fatcat:m4jr3fekz5aofakzb6gqtfsp6q

Embedded deep learning in ophthalmology: making ophthalmic imaging smarter

Petteri Teikari, Raymond P. Najjar, Leopold Schmetterer, Dan Milea
2019 Therapeutic Advances in Ophthalmology  
Despite these significant advances, little is known about the ability of various deep learning systems to be embedded within ophthalmic imaging devices, allowing automated image acquisition.  ...  Improved egde-layer performance via 'active acquisition' serves as an automatic data curation operator translating to better quality data in electronic health records, as well as on the cloud layer, for  ...  Acknowledgements The authors would like to acknowledge Professor Stephen Burns (Indiana University) for providing images to illustrate the adaptive optics deep learning correction.  ... 
doi:10.1177/2515841419827172 pmid:30911733 pmcid:PMC6425531 fatcat:gfujofoh7ze2pijspldjnztp74

Super-Resolving Compressed Video in Coding Chain [article]

Dewang Hou, Yang Zhao, Yuyao Ye, Jiayu Yang, Jian Zhang, Ronggang Wang
2021 arXiv   pre-print
Extensive experiments demonstrate the effectiveness of proposed innovations by comparing with state-of-the-art single image, video and reference-based restoration methods.  ...  Previous methods for enhancing the resolution of such videos often ignore the inherent interference between resolution loss and compression artifacts, which compromises perceptual video quality.  ...  It is known that, at low bit rates, a down-sampled video visually beats the HR video when represented with the same number of bits via compression.  ... 
arXiv:2103.14247v1 fatcat:36k2xfa7hvgxbofhrlmieglne4

Image reconstruction algorithms in radio interferometry: from handcrafted to learned regularization denoisers [article]

Matthieu Terris, Arwa Dabbech, Chao Tang, Yves Wiaux
2022 arXiv   pre-print
Firstly, we design a low dynamic range training database from optical intensity images. Secondly, we train a DNN denoiser at a noise level inferred from the signal-to-noise ratio of the data.  ...  The approach consists in learning a prior image model by training a deep neural network (DNN) as a denoiser, and substituting it for the handcrafted proximal regularization operator of an optimization  ...  Credits for the 32 images used in our training database go to NOIRLab/NSF/AURA/H.Schweiker/WIYN/T.A.Rector (University of Alaska Anchorage). The radio images where taken from: for Hercules A: R.  ... 
arXiv:2202.12959v2 fatcat:uysfazd6dbcjhp5chg6xz4egfe
« Previous Showing results 1 — 15 out of 297 results