Convolutional Sparse Coding for Image Super-Resolution

By Shuhang Gu, Wangmeng Zuo, Qi Xie, Deyu Meng, Xiangchu Feng, Lei Zhang. 2015

347 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

In Media Technology

Citations in the corpus

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, methodology): “rive the SR. This paradigm of self-similarity is also employed in Huang et al. [31], where self dictionaries are extended by further allowing for small transformations and shape variations. Gu et al. [25] proposed a convolutional sparse coding approach that improves consistency by processing the who”
Deep Image Prior (2017, methodology): “To obtain results for [25] we first decompose the corrupted image x0 into low and high frequency components similarly to [12] and run their method on the high frequency part.”
Ultra-Resolving Face Images by Discriminative Generative Networks (2016, methodology): “[7] proposes a sparse representation formulation by reconstructing corresponding LR and HR dictionaries, while [30] applies convolutional sparse coding instead of patch-based sparse coding.”
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (2016, methodology): “Traditional methods such as Total variation [24, 23], BM3D algorithm [5] and dictionary learning based methods [31, 10, 2] have shown very good performance on image restoration topics such as image denoising and super-resolution.”
End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks (2016, methodology): “Deep learning based methods have recently been applied to image SR and delivered compelling performance [19], [22], [23], [33].”
SRFeat: Single Image Super-Resolution with Feature Discrimination (2018, background): “neighborhood embedding [7, 45, 46, 36], sparse coding [52, 54, 51, 16], and local mapping function regression [15, 50, 38].”
Convolutional Neural Networks Analyzed via Convolutional Sparse Coding (2016, methodology): “However, in recent years an alternative to this patch-based processing has emerged in the form of the Convolutional Sparse Coding (CSC) model (Bristow et al., 2013; Kong and Fowlkes, 2014; Wohlberg, 2014; Gu et al., 2015; Heide et al., 2015; Papyan et al., 2016a,b).”
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss (2018, methodology): “Besides, there are some other methods, such as sparsity-based techniques [12, 19] and neighborhood embedding [11, 41], which have been widely used in real-world applications.”
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections (2016, neutral): “7 5.2 Image denoising . . . . . . . . . . . . . . 9 5.3 Image super-resolution . . . . . . . . . . 9 5.4 JPEG deblocking . . . . . . . . . . . . . 12 5.5 Image inpainting . . . . . . . . . . . . . 12”
Image Fusion With Convolutional Sparse Representation (2016, background): “multiple values of one pixel should be exactly the same to keep the consistency among overlapped patches [27].”
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network (2018, methodology): “xtended by [21] wherein self-dictionaries were constructed using self-similar patches that are related through small transformations and shape variations. The convolutional sparse coding framework in [19] process the whole image and exploits the consistency of neighboring patches to yield better ima”
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution (2015, methodology): “[16] develop a convolutional sparse coding based SR method.”
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (2023, background): “Traditional image SR methods primarily focus on designing more rational image priors based on our subjective knowledge, such as non-local similarity [26], low-rankness [27], sparsity [28, 29], and so on.”
Towards Robust Blind Face Restoration with Codebook Lookup Transformer (2022, positive): “Sparse representation with learned dictionaries has demonstrated its superiority in image restoration tasks, such as super-resolution [13, 33, 34, 41] and denoising [10].”