Proceedings Article10.1109/ICICEE.2012.15
MAP Based Blind Super-Resolution
Liu Gang,Hu Zhenlong +1 more
- 23 Aug 2012
- pp 26-28
5
TL;DR: This paper proposes a method which can adaptively estimate the blur parameter of a LR-image model and can greatly reduce the computation demand in super-resolution algorithms.
read more
Abstract: Super-resolution is the process of obtaining a high resolution image from multiple low resolution images. In most of the super-resolution algorithms, the blur parameter of a LR-image model always have to be manually set as a default value, this is not a good solution. In this paper, we propose a method which can adaptively estimate the blur parameter. Fusing all low-resolution images, we will get the initial image. When it is used in MAP algorithm, no more than 10 iterations is sufficient to get a stable solution. Compared with other MAP algorithms, this algorithm can greatly reduce the computation demand. Experiments show that when is applied to real image sequences, it can preserve the image edges and details. and the reconstructed image is clear. The propose algorithm is very deffient.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Image processing device, and image processing method
Takashi Shibata,剛志 柴田,Akihiko Iketani,彰彦 池谷,Shuji Senda,仙田 修司 +5 more
- 10 Dec 2012
TL;DR: In this paper, an image processing device is provided with a dictionary for storing at least two sets of data having associated therein a blurred patch and a restoration patch, and that generates a provisional restoration image from restoration patches selected on the basis of a value indicating the degree of similarity between blurred patches and a plurality of input patches generated by partitioning an externally-received input image.
18
Patent
Image processing device, image processing method and medium
Takashi Shibata,Akihiko Iketani,Shuji Senda +2 more
- 28 Nov 2013
TL;DR: In this article, an image processing device according to the present invention includes a weight calculation unit that determines an area where a feature value of an input image is saved, based on a gradient of a feature values of a pixel of the input image and a direction of the gradient, and calculates a weight for reducing a regularization constraint that is a constraint based on regularization of image processing in the area where the feature value is saved.
7
Superresolution of Hyperspectral Image Using Advanced Nonlocal Means Filter and Iterative Back Projection
TL;DR: An efficient superresolution algorithm based on advanced nonlocal means (NLM) filter and iterative back projection for hyperspectral image and the proposed ANLM utilizes the limited search to reduce the complexity is introduced.
Patent
Bildverarbeitungsvorrichtung und bildverarbeitungsverfahren
Shuji Senda,Takashi Shibata,Akihiko Iketani +2 more
- 05 Nov 2013
GCD Based Blind Super-Resolution for Remote Sensing Applications
Neerav Sharma,Praina Parimita Dash,Priyank Saxena +2 more
- 01 Jun 2018
TL;DR: The paper tries to overcome the limitations of the super resolution approach, known as blind super-resolution reconstruction approach, and the HR images obtained from this method is compared with the interpolated images.
References
Fast and robust multiframe super resolution
TL;DR: This paper proposes an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models and demonstrates its superiority to other super-resolution methods.
2.4K
Extraction of high-resolution frames from video sequences
TL;DR: A novel observation model based on motion compensated subsampling is proposed for a video sequence and Bayesian restoration with a discontinuity-preserving prior image model is used to extract a high-resolution video still given a short low-resolution sequence.
1.1K
A frequency domain approach to registration of aliased images with application to super-resolution
TL;DR: A frequency domain technique to precisely register a set of aliased images, based on their low-frequency, aliasing-free part, and a high-resolution image is then reconstructed using cubic interpolation.
Image sequence enhancement using sub-pixel displacements
Daniel Keren,Shmuel Peleg,R. Brada +2 more
- 05 Jun 1988
TL;DR: The subpixel registration allows image enhancement with respect to improved resolution and noise cleaning and is particularly useful for image sequences taken from an aircraft or satellite where images in a sequence differ mostly by translation and rotation.
Bayesian resolution enhancement of compressed video
TL;DR: This paper considers the impact of video compression on the super-resolution task, and utilizes the Bayesian framework to incorporate information from Hybrid motion-compensation and transform coding schemes to fuse thesuper-resolution and post-processing problems.
146