Jointly Optimized Regressors for Image Super‐resolution

Dai, Dengxin; Timofte, Radu; Gool, Luc Van

doi:10.1111/cgf.12544

Cited by 153 publications

(110 citation statements)

References 26 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…Then, a classifier is trained to predict the semantic concept related to each LR input patch and therefore the corresponding SR model to be used. A representative semanticbased method can be found in [17] where authors present a SR approach that make use of the Expectation-Maximisation (EM) algorithm to initially cluster the data and then a linear regression function can be learnt for each group.…”

Section: Current Limitations and Trendsmentioning

confidence: 99%

Sparse multi-modal probabilistic latent semantic analysis for single-image super-resolution

Fernández-Beltrán

Pla

2018

Signal Processing

View full text Add to dashboard Cite

This paper presents a novel single-image super-resolution (SR) approach based on latent topics in order to take advantage of the semantics pervading the topic space when super-resolving images. Image semantics has shown to be useful to relieve the ill-posed nature of the SR problem, however the most accepted clustering-based approach used to define semantic concepts limits the capability of representing complex visual relationships. The proposed approach provides a new probabilistic perspective where the SR process is performed according to the semantics encapsulated by a new topic model, the Sparse Multimodal probabilistic Latent Semantic Analysis (sMpLSA). Firstly, the sMpLSA model is formulated. Subsequently, a new SR framework based on sMpLSA is defined. Finally, an experimental comparison is conducted using seven learningbased SR methods over three different image datasets. Experiments reveal the potential of latent topics in SR by reporting that the proposed approach is able to provide a competitive performance.

show abstract

Section: Current Limitations and Trendsmentioning

confidence: 99%

Sparse multi-modal probabilistic latent semantic analysis for single-image super-resolution

Fernández-Beltrán

Pla

2018

Signal Processing

View full text Add to dashboard Cite

show abstract

“…Example-based learning methods have proven successful in learning from a collection of patch pairs: LR patches and corresponding HR patches [5,9,13,46]. In this section, we apply MI to example-based image super-resolution.…”

Section: Image Super-resolutionmentioning

confidence: 99%

“…In this section, we apply MI to example-based image super-resolution. In order to better show the advantage of MI, we follow the approaches which are directly based on k-NN search [5,9,18]. The very recent method JOR [9] was employed for comparison.…”

Section: Image Super-resolutionmentioning

confidence: 99%

“…In order to better show the advantage of MI, we follow the approaches which are directly based on k-NN search [5,9,18]. The very recent method JOR [9] was employed for comparison. JOR jointly learns a collection of regressors from LR patches to HR ones, which collectively yield the smallest super-resolving error for all training data, and selects the most appropriate regressor for each test patch via a voting scheme by its k nearest neighbors from the training samples.…”

Section: Image Super-resolutionmentioning

confidence: 99%

“…The method JOR + MI trained with 0.5 million patches is on par with the JOR trained with 5 million patches [9], but is considerably faster both at training and testing. The method also outperforms the very recent method SRCNN [13] using deep convolutional network, in terms of both performance and speed (in terms of speed at testing, SRCNN is on par with JOR trained from 5 million patches [9]). We also trained the method with 5 million patches, but observed no further improvement.…”

Section: Image Super-resolutionmentioning

confidence: 99%

See 2 more Smart Citations

Metric imitation by manifold transfer for efficient vision applications

Dai

Kroeger

Timofte

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Metric learning has proved very successful. However, human annotations are necessary. In this paper, we propose an unsupervised method, dubbed Metric Imitation (MI), where metrics over cheap features (target features, TFs) are learned by imitating the standard metrics over more sophisticated, off-the-shelf features (source features, SFs) by transferring view-independent property manifold structures. In particular, MI consists of: 1) quantifying the properties of source metrics as manifold geometry, 2) transferring the manifold from source domain to target domain, and 3) learning a mapping of TFs so that the manifold is approximated as well as possible in the mapped feature domain. MI is useful in at least two scenarios where: 1) TFs are more efficient computationally and in terms of memory than SFs; and 2) SFs contain privileged information, but are not available during testing. For the former, MI is evaluated on image clustering, category-based image retrieval, and instance-based object retrieval, with three SFs and three TFs. For the latter, MI is tested on the task of example-based image super-resolution, where high-resolution patches are taken as SFs and low-resolution patches as TFs. Experiments show that MI is able to provide good metrics while avoiding expensive data labeling efforts and that it achieves state-of-the-art performance for image super-resolution. In addition, manifold transfer is an interesting direction of transfer learning.

show abstract

Improving resolution of medical images with deep dense convolutional neural network

Wei

Jeon

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Doctors always desire high-resolution medical images to have accurate diagnosis. Super-resolution (SR) is a technology that can improve the resolution of medical images. Convolutional neural network (CNN)-based SR methods have achieved desired performance in natural images. In this paper, we apply a deep dense SR (DDSR) convolutional neural networks model to two types of medical images, including Computerized Tomography (CT) images and Magnetic Resonance imaging (MRI) images. This network densely connects every hidden layer to learn high-level features, which was first proposed for object recognition. A set of medical images is used for experiments. We compare the performance of DDSR with three state-of-the-art SR network models, including SR Convolutional Neural Network (SRCNN), Fast SR Convolutional Neural Network (FSRCNN), and Very Deep SR Convolutional Neural Network (VDSR). Both the objective indices and subjective evaluations are used for comparison. The results show that the proposed network has better performances both on CT and MRI images. KEYWORDS deep dense convolutional neural network, super-resolution, medical image 1 Concurrency Computat Pract Exper. 2020;32:e5084. wileyonlinelibrary.com/journal/cpe

show abstract

Jointly Optimized Regressors for Image Super‐resolution

Cited by 153 publications

References 26 publications

Sparse multi-modal probabilistic latent semantic analysis for single-image super-resolution

Sparse multi-modal probabilistic latent semantic analysis for single-image super-resolution

Metric imitation by manifold transfer for efficient vision applications

Improving resolution of medical images with deep dense convolutional neural network

Contact Info

Product

Resources

About