Image Super-Resolution with Fast Approximate Convolutional Sparse Coding

By Christian Osendorfer, Hubert Soyer, Patrick van der Smagt. 2014

81 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks (2015, background): “…ReLU denotes rectiﬁed linear units, lReLU denotes leaky rectiﬁed linear units (with leak rate 0.1), fc stands for a fully connected layer, conv for a convolutional layer and per-forated up-sampling denotes the deconvolution approach derived in Dosovitskiy et al. (2015) and Osendorfer et al. (2014).”
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images (2015, methodology): “As the up-sampling strategy we used simple “perforated” up-sampling as described in [38].”
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (2018, background): “Modern approaches to super-resolution are built on deep convolutional networks [5, 45, 27] as well as generative adversarial networks [18, 13] which use an adversarial loss to imagine high-resolution details in RGB images.”
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, methodology): “The other way to upscale a LR image is convolution with fractional stride of 1r in the LR space as mentioned by [24], which can be naively implemented by interpolation, perforate [27] or un-pooling [49] from LR space to HR space followed by a convolution with a stride of 1 in HR space.”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, background): “These applications include denoising [32, 5, 6, 20, 1], completion [35], super-resolution [10, 11, 9, 29], deblurring [30], deconvolution [36] and style transfer [16, 37], etc.”
Depth Map Super-Resolution by Deep Multi-Scale Guidance (2016, methodology): “In distinction to other single-image super resolution CNNs [11,12,22], our networks do not use a single fixed (non-trainable) upsampling operator.”
Deep Networks for Image Super-Resolution with Sparse Prior (2015, background): “Deep convolutional neural networks (CNN) [8] and deconvolutional networks [25] are designed that directly learn the non-linear mapping from LR space to HR space in a way similar to coupled sparse coding [35].”
End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks (2016, background): “This has also been noticed by [17], where they propose upsampling in a feature space rather than in the image domain.”
Deeply Improved Sparse Coding for Image Super-Resolution (2015, background): “More recently, inspired by the great success achieved by deep learning [16, 24, 27] in other computer vision tasks, people begin to use neural networks with deep architecture for image SR [5, 8, 22].”
Deep Joint Rain Detection and Removal from a Single Image (2016, background): “These applications include denoising [35, 6, 7, 21, 1], completion [38], super-resolution [11, 12, 10, 31], deblurring [32], deconvolution [39] and style transfer [17, 40], etc.”