Results 1 - 10
of
11
Bayesian methods for image super-resolution
- The Computer Journal
, 2007
"... We present a novel method of Bayesian image super-resolution in which marginalization is carried out over latent parameters such as geometric and photometric registration and the image pointspread function. Related Bayesian super-resolution approaches marginalize over the high-resolution image, nece ..."
Abstract
-
Cited by 26 (1 self)
- Add to MetaCart
We present a novel method of Bayesian image super-resolution in which marginalization is carried out over latent parameters such as geometric and photometric registration and the image pointspread function. Related Bayesian super-resolution approaches marginalize over the high-resolution image, necessitating the use of an unfavourable image prior, whereas our method allows for more realistic image prior distributions, and reduces the dimension of the integral considerably, removing the main computational bottleneck of algorithms such as Tipping and Bishop’s Bayesian image super-resolution. We show results on real and synthetic datasets to illustrate the efficacy of our method. 1.
Exact Feature Extraction using Finite Rate of Innovation Principles with an Application to Image Super-resolution
- IEEE TRANSACTIONS ON IMAGE PROCESSING
, 2008
"... The accurate registration of multiview images is of central importance in many advanced image processing applications. Image super-resolution, for example, is a typical application where the quality of the super-resolved image is degrading as registration errors increase. Popular registration method ..."
Abstract
-
Cited by 25 (9 self)
- Add to MetaCart
The accurate registration of multiview images is of central importance in many advanced image processing applications. Image super-resolution, for example, is a typical application where the quality of the super-resolved image is degrading as registration errors increase. Popular registration methods are often based on features extracted from the acquired images. The accuracy of the registration is in this case directly related to the number of extracted features and to the precision at which the features are located: images are best registered when many features are found with a good precision. However, in low-resolution images, only a few features can be extracted and often with a poor precision. By taking a sampling perspective, we propose in this paper new methods for extracting features in low resolution images in order to develop efficient registration techniques. We consider in particular the sampling theory of signals with finite rate of innovation [10] and show that some features of interest for registration can be retrieved perfectly in this framework, thus allowing an exact registration. We also demonstrate through simulations that the sampling model which enables the use of finite rate of innovation principles is well-suited for modeling the acquisition of images by a camera. Simulations of image registration and image super-resolution of artificially sampled images are first presented, analyzed and compared to traditional techniques. We finally present favorable experimental results of super-resolution of real images acquired by a digital camera available on the market.
Bayesian image super-resolution, continued
- Advances in Neural Information Processing Systems
, 2006
"... This paper develops a multi-frame image super-resolution approach from a Bayesian view-point by marginalizing over the unknown registration parameters relating the set of input low-resolution views. In Tipping and Bishop’s Bayesian image super-resolution approach [16], the marginalization was over t ..."
Abstract
-
Cited by 11 (3 self)
- Add to MetaCart
This paper develops a multi-frame image super-resolution approach from a Bayesian view-point by marginalizing over the unknown registration parameters relating the set of input low-resolution views. In Tipping and Bishop’s Bayesian image super-resolution approach [16], the marginalization was over the superresolution image, necessitating the use of an unfavorable image prior. By integrating over the registration parameters rather than the high-resolution image, our method allows for more realistic prior distributions, and also reduces the dimension of the integral considerably, removing the main computational bottleneck of the other algorithm. In addition to the motion model used by Tipping and Bishop, illumination components are introduced into the generative model, allowing us to handle changes in lighting as well as motion. We show results on real and synthetic datasets to illustrate the efficacy of this approach. 1
A Zisserman. Optimizing and learning for super-resolution
- In In Proceedings of the British Machine Vision Conference
, 2006
"... In multiple-image super-resolution, a high resolution image is estimated from a number of lower-resolution images. This involves computing the parameters of a generative imaging model (such as geometric and photometric registration, and blur) and obtaining a MAP estimate by minimizing a cost functio ..."
Abstract
-
Cited by 8 (3 self)
- Add to MetaCart
(Show Context)
In multiple-image super-resolution, a high resolution image is estimated from a number of lower-resolution images. This involves computing the parameters of a generative imaging model (such as geometric and photometric registration, and blur) and obtaining a MAP estimate by minimizing a cost function including an appropriate prior. We consider the quite general geometric registration situation modelled by a plane projective transformation, and make two novel contributions: (i) in previous approaches the MAP estimate has been obtained by first computing and fixing the registration, and then computing the super-resolution image with this registration. We demonstrate that superior estimates are obtained by optimizing over both the registration and image; (ii) the parameters of the edge preserving prior are learnt automatically from the data, rather than being set by trial and error. We show examples on a number of real sequences including multiple stills, digital video, and DVDs of movies. 1
Super-Resolution Using Sub-band Constrained Total Variation
"... Abstract. Super-resolution of a single image is a severely ill-posed prob-lem in computer vision. It is possible to consider solving this problem by considering a total variation based regularization framework. The choice of total variation based regularization helps in formulating an edge pre-servi ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Super-resolution of a single image is a severely ill-posed prob-lem in computer vision. It is possible to consider solving this problem by considering a total variation based regularization framework. The choice of total variation based regularization helps in formulating an edge pre-serving scheme for super-resolution. However, this scheme tends to re-sult in a piece-wise constant resultant image. To address this issue, we extend the formulation by incorporating an appropriate sub-band con-straint which ensures the preservation of textural details in trade off with noise present in the observation. The proposed framework is extensively evaluated and the experimental results for the same are presented. 1
Research Article Overcoming Registration Uncertainty in Image Super-Resolution: Maximize or Marginalize?
, 2007
"... In multiple-image super-resolution, a high-resolution image is estimated from a number of lower-resolution images. This usually involves computing the parameters of a generative imaging model (such as geometric and photometric registration, and blur) and obtaining a MAP estimate by minimizing a cost ..."
Abstract
- Add to MetaCart
In multiple-image super-resolution, a high-resolution image is estimated from a number of lower-resolution images. This usually involves computing the parameters of a generative imaging model (such as geometric and photometric registration, and blur) and obtaining a MAP estimate by minimizing a cost function including an appropriate prior. Two alternative approaches are examined. First, both registrations and the super-resolution image are found simultaneously using a joint MAP optimization. Second, we perform Bayesian integration over the unknown image registration parameters, deriving a cost function whose only variables of interest are the pixel values of the super-resolution image. We also introduce a scheme to learn the parameters of the image prior as part of the super-resolution algorithm. We show examples on a number of real sequences including multiple stills, digital video, and DVDs of movies. Copyright © 2007 Lyndsey C. Pickup et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 1.
Getting the Face Behind the Squares: Reconstructing Pixelized Video Streams
"... Pixelization is a technique to make parts of an image impossible to discern by the human eye by artificially decreasing the image resolution. Pixelization, as other forms of image censorship, is effective at hiding parts of an image that might be offensive to the viewer. However, pixelization is als ..."
Abstract
- Add to MetaCart
(Show Context)
Pixelization is a technique to make parts of an image impossible to discern by the human eye by artificially decreasing the image resolution. Pixelization, as other forms of image censorship, is effective at hiding parts of an image that might be offensive to the viewer. However, pixelization is also often used also to achieve anonymity, for example to make the features of a person’s face unrecognizable or the defining characteristics of cars and building unidentifiable. This use of pixelization is somewhat effective in the case of still images, even though it is open to dictionary attacks. However, when used in videos, pixelization might be vulnerable to full reconstruction attacks. In this paper, we describe an attack against the anonymization of videos through pixelization. We develop an approach that, given a pixelized video, reconstructs the image being pixelized so that the human eye can clearly identify the object being protected. We implemented our approach and tested it against both artificial and real-world videos. The results of our experiments show that, in many cases, video pixelization does not provide sufficient guarantees of anonymity. 1
IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Exact Feature Extraction using Finite Rate of Innovation Principles with an Application to Image Super-resolution
"... The accurate registration of multiview images is of central importance in many advanced image processing applications. Image super-resolution, for example, is a typical application where the quality of the super-resolved image is degrading as registration errors increase. Popular registration method ..."
Abstract
- Add to MetaCart
(Show Context)
The accurate registration of multiview images is of central importance in many advanced image processing applications. Image super-resolution, for example, is a typical application where the quality of the super-resolved image is degrading as registration errors increase. Popular registration methods are often based on features extracted from the acquired images. The accuracy of the registration is in this case directly related to the number of extracted features and to the precision at which the features are located: images are best registered when many features are found with a good precision. However, in low-resolution images, only a few features can be extracted and often with a poor precision. By taking a sampling perspective, we propose in this paper new methods for extracting features in low resolution images in order to develop efcient registration techniques. We consider in particular the sampling theory of signals with nite rate of innovation [10] and show that some features of interest for registration can be retrieved perfectly in this framework, thus allowing an exact registration. We also demonstrate through simulations that the sampling model which enables the use of nite rate of innovation principles is well-suited for modeling the acquisition of images by a camera. Simulations of image registration and image super-resolution of articially sampled images are rst presented, analyzed and compared to traditional techniques. We nally present favorable experimental results of super-resolution of real images acquired by a digital camera available on the market. I.
