1,994 Hits in 5.3 sec

Dictionary Replacement for Single Image Restoration of 3D Scenes

NimishaT M, Arun Mathamkode, Rajagopalan Ambasamudram
2016 Procedings of the British Machine Vision Conference 2016   unpublished
In this paper, we address the problem of jointly estimating the latent image and the depth/blur map from a single space-variantly blurred image using dictionary replacement.  ...  Let Y be the observed blurred image of a 3D scene and h 0 be the blur kernel corresponding to the most blurred region in the image.  ...  single space-variantly blurred image using dictionary replacement.  ... 
doi:10.5244/c.30.32 fatcat:odku7b3mvzew7jdo54z5lyhavq

Hyperspectral video restoration using optical flow and sparse coding

Ajmal Mian, Richard Hartley
2012 Optics Express  
Spectral restoration is followed by spatial restoration using a guided dictionary approach where one dictionary is learned for measured bands and another for a band that is to be spatially restored.  ...  Optical flow errors are corrected by exploiting sparsity in the spectra and the spatial correlation between images of a scene at different wavelengths.  ...  Optical flow in the horizontal direction for the scene inFig. 4represented as 3D plots.  ... 
doi:10.1364/oe.20.010658 pmid:22565691 fatcat:mrekhtdipfgkfavtmbnmw4sz4m

Compressive Hyperspectral Imaging With Side Information

Xin Yuan, Tsung-Han Tsai, Ruoyu Zhu, Patrick Llull, David Brady, Lawrence Carin
2015 IEEE Journal on Selected Topics in Signal Processing  
By using RGB images as side information of the compressive sensing system, the proposed approach is extended to learn a coupled dictionary from the joint dataset of the compressed measurements and the  ...  The inversion algorithm learns a dictionary in situ from the measurements via global-local shrinkage priors.  ...  Particularly, the proposed algorithm learns a joint dictionary from a single CASSI measurement and the corresponding RGB image (of the same scene) and then reconstructs the hyperspectral datacube.  ... 
doi:10.1109/jstsp.2015.2411575 fatcat:v54lrrop5nhshlcyrzdaltjua4

ICP [chapter]

2014 Computer Vision  
Definition An image decomposition is the result of a mathematical transformation of an image into a new set of images I 376 Image Enhancement and Restoration 6.  ...  Definition The purpose of illumination estimation is to determine the direction, intensity, and/or color of the lighting in a scene.  ...  An important advantage of the latter is its superior image quality, compared with 3D model building for complicated real world scenes.  ... 
doi:10.1007/978-0-387-31439-6_100030 fatcat:kfm7gu7zenb6tlz5qu26dvf3q4

Antialiasing recovery

Lei Yang, Pedro V. Sander, Jason Lawrence, Hugues Hoppe
2011 ACM Transactions on Graphics  
We present a method for restoring antialiased edges that are damaged by certain types of nonlinear image filters.  ...  Our prototype system can process up to 500 megapixels per second and we present results for a number of different image filters.  ...  We are grateful to Yongjin Kim, MartinČadík, Johannes Kopf, Jan Eric Kyprianidis, Giuseppe Papari and Phillip Greenspun, as well as the following Flickr R users for sharing their images: paullew, shoshonasnow  ... 
doi:10.1145/1966394.1966401 fatcat:36mq6flrjrg37fzn5teojievca

Learnable Reconstruction Methods from RGB Images to Hyperspectral Imaging: A Survey [article]

Jingang Zhang and Runmu Su and Wenqi Ren and Qiang Fu and Yunfeng Nie
2021 arXiv   pre-print
However, the devices for acquiring hyperspectral images are expensive and complicated.  ...  We present a thorough investigation of these state-of-the-art spectral reconstruction methods from the widespread RGB images.  ...  ACKNOWLEDGMENT The authors would like to thank the authors of Sparse Coding, HSCNN, SR2D/3DNet, SRUNet, SRMSCNN, and etc. for providing open-source code.  ... 
arXiv:2106.15944v1 fatcat:zisfnjrs3nfkjexubp7f4esk4a

Compressive Sensing Hyperspectral Imaging by Spectral Multiplexing with Liquid Crystal

Yaniv Oiknine, Isaac August, Vladimir Farber, Daniel Gedalin, Adrian Stern
2018 Journal of Imaging  
The redundancy of the information motivates our quest to implement Compressive Sensing (CS) theory for HS imaging.  ...  The outstanding advantage of the CS-MUSI camera is that the entire HS image is captured from an order of magnitude fewer measurements of the sensor array, compared to conventional HS imaging methods.  ...  ) for providing the liquid crystal cell.  ... 
doi:10.3390/jimaging5010003 pmid:34470182 fatcat:v7mcmsnh5zgrjhmfb3vpwitsl4

Depth map denoising using graph-based transform and group sparsity

Wei Hu, Xin Li, Gene Cheung, Oscar Au
2013 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)  
In this paper, we build on two previously developed works in the image denoising literature to restore single depth maps-i.e., to jointly exploit local smoothness and nonlocal self-similarity of a depth  ...  Experimental results show that for single depth maps corrupted with additive white Gaussian noise (AWGN), our proposed NLGBT denoising algorithm can outperform state-ofthe-art image denoising methods such  ...  3D scene and the capturing camera) widely affordable.  ... 
doi:10.1109/mmsp.2013.6659254 dblp:conf/mmsp/HuLCA13 fatcat:msknlzwixrfzxbk4osh7d4rdk4

High Fidelity Single-Pixel Imaging

Chao Deng, Xuemei Hu, Xiaoxu Li, Jinli Suo, Zhili Zhang, Qionghai Dai
2019 IEEE Photonics Journal  
Index Terms: Single-pixel imaging, high fidelity, sparse coding, local prior.  ...  Abstract: Single-pixel imaging (SPI) is an emerging technique which has attracted wide attention in various fields.  ...  We can also learn the dictionary for a specific target scene for higher precision, and thus has the potential to broaden the practical application of single-pixel imaging.  ... 
doi:10.1109/jphot.2019.2900549 fatcat:4e3ctewyyzadvnformrxca2sya

Scene Text Deblurring in Non-stationary Video Sequences

Margarita Favorskaya, Vladimir Buryachenko
2016 Procedia Computer Science  
The text as a linguistic component provides a significant amount of information for scene understanding, scene categorization, image retrieval, and many other challenging problems.  ...  Also, the blind technique of a blurred text restoration is discussed. Additionally some results of the text detection are mentioned.  ...  Acknowledgments This work was supported by the Russian Fund for Basic Researches, grant number 16-07-00121 A.  ... 
doi:10.1016/j.procs.2016.08.259 fatcat:ugoduvc2fzborovgfbzthzqkpm

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
for Topology Classification of Local 3D Structures Okutomi, Masatoshi Image Restoration and Disparity Estimation from an Uncalibrated Multi-Layered Image Direct Image Alignment of Projector-Camera  ...  Scenes Shape-based Similarity Retrieval of Doppler Images for Clinical Decision Support Türetken, Engin Delineating Trees in Noisy 2D Images and 3D Image-Stacks Turk, Matthew Workshop: Location-based  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Ensemble Dictionary Learning for Single Image Deblurring via Low-Rank Regularization

Jinyang Li, Zhijing Liu
2019 Sensors  
In this paper, an improved sparse representation model regularized by a low-rank constraint is proposed for single image deblurring.  ...  The key motivation for the proposed model lies in the observation that natural images are full of self-repetitive structures and they can be represented by similar patterns.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s19051143 fatcat:zeowvlucbfafhihaxnk4j7xbii

Unveiling the invisible - mathematical methods for restoring and interpreting illuminated manuscripts [article]

Luca Calatroni, Marie d'Autume, Rob Hocking, Stella Panayotova, Simone Parisotto, Paola Ricciardi, Carola-Bibiane Schönlieb
2018 Heritage Science   pre-print
In this paper we discuss a range of mathematical methods for digital image restoration and digital visualisation for illuminated manuscripts.  ...  The last fifty years have seen an impressive development of mathematical methods for the analysis and processing of digital images, mostly in the context of photography, biomedical imaging and various  ...  ) grant EP/L016516/1 for the University of Cambridge Centre for Doctoral Training, the Cambridge Centre for Analysis.  ... 
doi:10.1186/s40494-018-0216-z pmid:31258910 pmcid:PMC6559148 arXiv:1803.07187v1 fatcat:hs7wkwiqzfhehcsx4bumeqtvsm

Rain Streaks and Snowflakes Removal for Video Sequences via Motion Compensation and Matrix Completion

Yutong Zhou, Nobutaka Shimada
2020 SN Computer Science  
We then employ the online dictionary learning for sparse representation technique, and SVM classifier to eliminate parts that are not rain streaks.  ...  Image and video deraining tasks aim to reconstruct original scenes, from which human vision and computer vision systems can better identify objects and more details present in images and video sequences  ...  Compliance with Ethical Standards Conflict of interest The authors declare that they have no conflict of interest.  ... 
doi:10.1007/s42979-020-00333-6 fatcat:55jnxg3x4fh3nknlpjlc3otaym

Bidirectional 3D Quasi-Recurrent Neural Networkfor Hyperspectral Image Super-Resolution

Ying Fu, Zhiyuan Liang, Shaodi You
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this article, we design a bidirectional 3D quasi-recurrent neural network for HSI super-resolution with arbitrary number of bands.  ...  Extensive evaluations and comparisons on HSI super-resolution demonstrate improvements over state-of-the-art methods, in terms of both restoration accuracy and visual quality.  ...  [11] made a step forward by investigating how to adapt state-of-the-art residual learning-based single gray/RGB image super-resolution approaches for computationally efficient single HSI super-resolution  ... 
doi:10.1109/jstars.2021.3057936 fatcat:522lja4s65bbhhcm62lrelueby
« Previous Showing results 1 — 15 out of 1,994 results