Results 11 - 20
of
53
Generalized Face Super-Resolution
"... Abstract—Existing learning-based face super-resolution (hallucination) techniques generate high-resolution images of a single facial modality (i.e., at a fixed expression, pose and illumination) given one or set of low-resolution face images as probe. Here, we present a generalized approach based on ..."
Abstract
-
Cited by 8 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Existing learning-based face super-resolution (hallucination) techniques generate high-resolution images of a single facial modality (i.e., at a fixed expression, pose and illumination) given one or set of low-resolution face images as probe. Here, we present a generalized approach based on a hierarchical tensor (multilinear) space representation for hallucinating high-resolution face images across multiple modalities, achieving generalization to variations in expression and pose. In particular, we formulate a unified tensor which can be reduced to two parts: a global image-based tensor for modeling the mappings among different facial modalities, and a local patch-based multiresolution tensor for incorporating high-resolution image details. For realistic hallucination of unregistered low-resolution faces contained in raw images, we develop an automatic face alignment algorithm capable of pixel-wise alignment by iteratively warping the probing face to its projection in the space of training face images. Our experiments show not only performance superiority over existing benchmark face super-resolution techniques on single modal face hallucination, but also novelty of our approach in coping with multimodal hallucination and its robustness in automatic alignment under practical imaging conditions. Index Terms—Face hallucination, super-resolution, tensor. I. PROBLEM STATEMENT
Joint Demosaicing and Super-Resolution Imaging from a Set of Unregistered Aliased Images
"... We present a new algorithm that performs demosaicing and super-resolution jointly from a set of raw images sampled with a color filter array. Such a combined approach allows us to compute the alignment parameters between the images on the raw camera data before interpolation artifacts are introduced ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
We present a new algorithm that performs demosaicing and super-resolution jointly from a set of raw images sampled with a color filter array. Such a combined approach allows us to compute the alignment parameters between the images on the raw camera data before interpolation artifacts are introduced. After image registration, a high resolution color image is reconstructed at once using the full set of images. For this, we use normalized convolution, an image interpolation method from a nonuniform set of samples. Our algorithm is tested and compared to other approaches in simulations and practical experiments.
A Lorentzian Stochastic Estimation for a Robust Iterative Multiframe Super-Resolution Reconstruction with Lorentzian-Tikhonov Regularization
, 2007
"... Recently, there has been a great deal of work developing super-resolution reconstruction (SRR) algorithms. While many such algorithms have been proposed, the almost SRR estimations are based on L1 or L2 statistical norm estimation, therefore these SRR algorithms are usually very sensitive to their a ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
Recently, there has been a great deal of work developing super-resolution reconstruction (SRR) algorithms. While many such algorithms have been proposed, the almost SRR estimations are based on L1 or L2 statistical norm estimation, therefore these SRR algorithms are usually very sensitive to their assumed noise model that limits their utility. The real noise models that corrupt the measure sequence are unknown; consequently, SRR algorithm using L1 or L2 norm may degrade the image sequence rather than enhance it. Therefore, the robust norm applicable to several noise and data models is desired in SRR algorithms. This paper first comprehensively reviews the SRR algorithms in this last decade and addresses their shortcomings, and latter proposes a novel robust SRR algorithm that can be applied on several noise models. The proposed SRR algorithm is based on the stochastic regularization technique of Bayesian MAP estimation by minimizing a cost function. For removing outliers in the data, the Lorentzian error norm is used for measuring the difference between the projected estimate of the high-resolution image and each low-resolution image. Moreover, Tikhonov regularization and Lorentzian-Tikhonov regularization are used to remove artifacts from the final answer and improve the rate of convergence. The experimental results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods based on L1 and L2 norms for several noise models such as noiseless, additive white Gaussian noise (AWGN), poisson noise, salt and pepper noise, and speckle noise.
Optimization transfer approach to joint registration/reconstruction for motion-compensated image reconstruction," presented at the ISBI
, 2010
"... Motion artifacts in image reconstruction problems can be reduced by performing image motion estimation and image reconstruction jointly using a penalized-likelihood cost func-tion. However, updating the motion parameters by conven-tional gradient-based iterations can be computationally de-manding du ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
Motion artifacts in image reconstruction problems can be reduced by performing image motion estimation and image reconstruction jointly using a penalized-likelihood cost func-tion. However, updating the motion parameters by conven-tional gradient-based iterations can be computationally de-manding due to the system model required in inverse prob-lems. This paper describes an optimization transfer approach that leads to minimization steps for the motion parameters that have comparable complexity to those needed in image registration problems. This approach can simplify the imple-mentation of motion-compensated image reconstruction (MCIR) methods when the motion parameters are estimated jointly with the reconstructed image.
A majorization-minimization approach to total variation reconstruction of super-resolved images
- in 16th European Signal Processing Conf
, 2008
"... Super-resolution is the task of reconstructing high-resolution images from shifted, rotated, low-resolution degraded obser-vations. It can be formulated as an inverse problem for which regularization is necessary. In this paper we adopt this for-mulation and use the Total-Variation criterion for reg ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Super-resolution is the task of reconstructing high-resolution images from shifted, rotated, low-resolution degraded obser-vations. It can be formulated as an inverse problem for which regularization is necessary. In this paper we adopt this for-mulation and use the Total-Variation criterion for regulariza-tion. Then, we employ the Majorization-Minimization (MM) methodology to reconstuct high-resolution images from low-resolution observations. Experimental results are shown, which demonstrate the advantages of the proposed algorithm compared to other methods. 1.
Super-Resolution Reconstruction Algorithm To MODIS Remote Sensing Images
, 2007
"... In this paper, we propose a super-resolution image reconstruction algorithm to moderate-resolution imaging spectroradiometer (MODIS) remote sensing images. This algorithm consists of two parts: registration and reconstruction. In the registration part, a truncated quadratic cost function is used to ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
In this paper, we propose a super-resolution image reconstruction algorithm to moderate-resolution imaging spectroradiometer (MODIS) remote sensing images. This algorithm consists of two parts: registration and reconstruction. In the registration part, a truncated quadratic cost function is used to exclude the outlier pixels, which strongly deviate from the registration model. Accurate photometric and geometric registration parameters can be obtained simultaneously. In the reconstruction part, the L1 norm data fidelity term is chosen to reduce the effects of inevitable registration error, and a Huber prior is used as regularization to preserve sharp edges in the reconstructed image. In this process, the outliers are excluded again to enhance the robustness of the algorithm. The proposed algorithm has been tested using real MODIS band-4 images, which were captured in different dates. The experimental results and comparative analyses verify the effectiveness of this algorithm.
An Analysis of Color Demosaicing in Plenoptic Cameras
"... A plenoptic camera captures the 4D radiance about a scene. Recent practical solutions mount a microlens array on top of a commodity SLR to directly acquire these rays. However, they suffer from low resolution as hundreds of thousands of views need to be captured in a single shot. In this paper, we d ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
A plenoptic camera captures the 4D radiance about a scene. Recent practical solutions mount a microlens array on top of a commodity SLR to directly acquire these rays. However, they suffer from low resolution as hundreds of thousands of views need to be captured in a single shot. In this paper, we develop a simple but effective technique for improving the image resolution of the plenoptic camera by maneuvering the demosaicing process. We first show that the traditional solution by demosaicing each individual microlens image and then blending them for view synthesis is suboptimal. In particular, this demosaicing process often suffers from aliasing artifacts, and it damages high frequency information recorded by each microlens image hence degrades the image quality. We instead propose to demosaic the synthesized view at the rendering stage. Specifically, we first transform the radiance to the desired focal plane and then apply frequency domain plenoptic resampling. A full resolution color filtered image is then created by performing a 2D integral projection from the reparameterized radiance. Finally, we conduct demosacing to obtain the color result. We show that our solution can achieve visible resolution enhancement on dynamic refocusing and depth-assisted deep focus rendering. 1.
Demosaicing by Smoothing along 1D Features
"... Most digital cameras capture color pictures in the form of an image mosaic, recording only one color channel at each pixel position. Therefore, an interpolation algorithm needs to be applied to reconstruct the missing color information. In this paper we present a novel Bayer pattern demosaicing appr ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Most digital cameras capture color pictures in the form of an image mosaic, recording only one color channel at each pixel position. Therefore, an interpolation algorithm needs to be applied to reconstruct the missing color information. In this paper we present a novel Bayer pattern demosaicing approach, employing stochastic global optimization performed on a pixel neighborhood. We are minimizing a newly developed cost function that increases smoothness along one-dimensional image features. While previous algorithms have been developed focusing on LDR images only, our optimization scheme and the underlying cost function are designed to handle both LDR and HDR images, creating less demosaicing artifacts, compared to previous approaches. 1.
Constrained, globally optimal, multi-frame motion estimation
- Proc. 2005 IEEE Workshop on Statistical Signal Processing
, 2005
"... We address the problem of estimating the relative motion between the frames of a video sequence. In comparison with the commonly applied pairwise image registration methods, we consider global consistency conditions for the overall multi-frame motion estimation problem, which is more accurate. We re ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
We address the problem of estimating the relative motion between the frames of a video sequence. In comparison with the commonly applied pairwise image registration methods, we consider global consistency conditions for the overall multi-frame motion estimation problem, which is more accurate. We review the recent work on this subject and propose an optimal framework, which can apply the consistency conditions as both hard constraints in the estimation problem, or as soft constraints in the form of stochastic (Bayesian) priors. The framework is applicable to virtually any motion model and enables us to develop a robust approach, which is resilient against the effects of outliers and noise. The effectiveness of the proposed approach is confirmed by a super-resolution application on synthetic and real data sets. 1.
