Deeply-Recursive Convolutional Network for Image Super-Resolution

Kim, Jiwon; Lee, Jung Kwon; Lee, Kyoung Mu

doi:10.48550/arxiv.1511.04491

Cited by 33 publications

(21 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parameter number PSNR SRCNN [20] 57,184 32.59 FSRCNN [44] 15,740 33.06 VDSR [42] 664,704 Methods and metrics: We compare our model with several recent state-of-the-art methods, including a three-layer CNN (SRCNN) [20], superresolution forest (SRF) [53], sparse coding-based network (SCN) [22], anchored neighborhood regression (A+) [23], shepard interpolation neural network (ShCNN) [21], very deep convolutional network (VDSR) [23], and fast convolutional network for SR (FSRCNN) [44]. For fair comparisons, we employ the popular PSNR and SSIM metrics for evaluation.…”

Section: Methodsmentioning

confidence: 99%

“…More recently, researchers notice the importance of image details and make various of attempts for exploration. Kim et al [23], [42] further improved the SR quality by different network architectures such as very deep and recursive network structures. However, these methods heavily rely on very deep networks with plenty of parameters.…”

Section: Deep Learning In Image Super-resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Structure-Preserving Image Super-Resolution via Contextualized Multitask Learning

Shi

Wang

Chen

et al. 2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Single image super resolution (SR), which refers to reconstruct a higher-resolution (HR) image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the breakthroughs of recently proposed SR methods using convolutional neural networks (CNNs), their generated results usually lack of preserving structural (high-frequency) details. In this paper, regarding global boundary context and residual context as complimentary information for enhancing structural details in image restoration, we develop a contextualized multi-task learning framework to address the SR problem. Specifically, our method first extracts convolutional features from the input LR image and applies one deconvolutional module to interpolate the LR feature maps in a content-adaptive way. Then, the resulting feature maps are fed into two branched sub-networks. During the neural network training, one sub-network outputs salient image boundaries and the HR image, and the other sub-network outputs the local residual map, i.e., the residual difference between the generated HR image and ground-truth image. On several standard benchmarks (i.e., Set5, Set14 and BSD200), our extensive evaluations demonstrate the effectiveness of our SR method on achieving both higher restoration quality and computational efficiency compared with several stateof-the-art SR approaches. 1

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Deep Learning In Image Super-resolutionmentioning

confidence: 99%

Structure-Preserving Image Super-Resolution via Contextualized Multitask Learning

Shi

Wang

Chen

et al. 2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…Kim et al [13] proposed an image SR method using a Deeply-Recursive Convolutional Network (DRCN), which contains deep CNNs with up to 20 layers. Consequently, the model has a huge number of parameters.…”

Section: Super-resolution (Sr)mentioning

confidence: 99%

Selfie Periocular Verification using an Efficient Super-Resolution Approach

Tapia¹,

Valenzuela²,

Lara³

et al. 2021

Preprint

View full text Add to dashboard Cite

Selfie-based biometrics has great potential for a wide range of applications from marketing to higher security environments like online banking. This is now especially relevant since e.g. periocular verification is contactless, and thereby safe to use in pandemics such as COVID-19. However, selfie-based biometrics faces some challenges since there is limited control over the data acquisition conditions. Therefore, super-resolution have to be used to increase the quality of the captured images. Most of the state of the art super-resolution methods use deep networks with large filters, thereby needing to train and store a correspondingly large number of parameters, and making their use difficult for mobile devices commonly used for selfie-based.In order to achieve an efficient super-resolution method, we propose an Efficient Single Image Super-Resolution (ESISR) algorithm, which takes into account a trade-off between the efficiency of the deep neural network and the size of its filters. To that end, the method implements a novel loss function based on the Sharpness metric. This metric turns out to be more suitable for increasing the quality of the eye images. Our method drastically reduces the number of parameters when compared with Deep CNNs with Skip Connection and Network (DCSCN): from 2,170,142 to 28,654 parameters when the image size is increased by a factor of x3. Furthermore, the proposed method keeps the sharp quality of the images, which is highly relevant for biometric recognition purposes. The results on remote verification systems with raw images reached an Equal Error Rate (EER) 8.7% for FaceNet and 10.05% for VGGFace. Where embedding vectors were used from periocular images the best results reached an EER of 8.9% (x3) for FaceNet and 9.90% (x4) for VGGFace.

show abstract

“…Nevertheless, that is not true in practice and training very deep NN is very challenging due to problems like vanishing gradients causing the NN to not be able to learn simple functions like the identity function between input and output [Sussillo and Abbott, 2015;Hochreiter et al, 2001]. The usual way to train DNNs is through residual blocks [He et al, 2015;Zagoruyko and Komodakis, 2017;Lim et al, 2017;Kim et al, 2016]. With residual blocks the NN itself can choose it's depth by skipping the training of a few layers using skip connections.…”

Section: Input-outputmentioning

confidence: 99%

A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features

Krokos,

Xuan,

Bordas

et al. 2020

Preprint

View full text Add to dashboard Cite

Finite Element Analysis (FEA) for stress prediction in structures with microstructural features is computationally expensive since those features are much smaller than the other geometric features of the structure. The accurate prediction of the additional stress generated by such microstructural features therefore requires a very fine FE mesh. Omitting or averaging the effect of the microstructural features from FEA models is standard practice, resulting in faster calculations of global stress fields, which, assuming some degree of scale separability, may then be complemented by local defect analyses. The purpose of this work is to train an Encoder-Decoder Convolutional Neural Networks (CNN) to automatically add local fine-scale stress corrections to coarse stress predictions around defects. We wish to understand to what extent such a framework may provide reliable stress predictions inside and outside the training set, i.e. for unseen coarse scale geometries and stress distributions and/or unseen defect geometries. Ultimately, we aim to develop efficient offline data generation and online data acquisition methods to maximise the domain of validity of the CNN predictions. To achieve these ambitious goals, we will deploy a Bayesian approach providing not point estimates, but credible intervals of the fine-scale stress field, as a means to evaluate the uncertainty of the predictions. The uncertainty quantified by the network will automatically encompass the lack of knowledge due to unseen macro and micro features, and the lack of knowledge due to the potential lack of scale separability. This uncertainty will be used in a Selective Learning framework to reduce the data requirements of the network. In this work we will investigate stress prediction in 2D composite structures with randomly distributed circular pores.

show abstract

Deeply-Recursive Convolutional Network for Image Super-Resolution

Cited by 33 publications

References 14 publications

Structure-Preserving Image Super-Resolution via Contextualized Multitask Learning

Structure-Preserving Image Super-Resolution via Contextualized Multitask Learning

Selfie Periocular Verification using an Efficient Super-Resolution Approach

A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features

Contact Info

Product

Resources

About