PSyCo: Manifold Span Reduction for Super Resolution

By Eduardo Pérez-Pellitero, Jordi Salvador, Javier Ruiz-Hidalgo, Bodo Rosenhahn. 2016

48 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models

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

1. Luc Van Gool
2. Radu Timofte
3. Ming-Hsuan Yang
4. Lei Zhang
5. Yun Raymond Fu
6. Chen Change Loy
7. Kai Zhang
8. Chao Dong

In Media Technology

1. Radu Timofte
2. Saeed Anwar
3. Nick Barnes
4. Kai Zhang
5. Chao Dong
6. Luc Van Gool
7. Yulun Zhang
8. Lei Zhang

In Generative Models

1. Saeed Anwar
2. Nick Barnes
3. Radu Timofte
4. Bernhard Schölkopf
5. Michael Hirsch
6. Eirikur Agustsson
7. Matthew A. Brown
8. Ki Sang Hong

Citations in the corpus

• EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, background): “They further include dictionary-based methods [33, 40, 52, 59, 61, 64] that learn a sparse representation of image patches as a combination of dictionary atoms, as well as neural network-based approaches [4, 8, 9, 24, 25, 26, 47, 48, 62] which apply convolutional neural networks (CNNs) to the task…”
• Image Super-Resolution Using Very Deep Residual Channel Attention Networks (2018, methodology): “We use 4 stat-of-the-art methods (e.g., DRCN [19], FSRCNN [2], PSyCo [45], and ENet-E [8]) to upscale the LR images and then calculate their accuracies.”
• Frame-Recurrent Video Super-Resolution (2018, methodology): “Super-resolution is a classic ill-posed inverse problem with approaches ranging from simple interpolation methods such as Bilinear, Bicubic and Lanczos [8] to example-based super-resolution [11, 12, 37, 39], dictionary learning [30, 40], and self-similarity approaches [15, 38].”
• 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].”
• NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study (2017, methodology): “We use a selection of methods from [48, 49, 33], the seminal CNN methods [9, 21, 26], and additionally a selfsimilarity based method [19].”
• Densely Residual Laplacian Super-Resolution (2019, methodology): “We compare with six methods i.e. Bicubic, DRCN [13], FSRCNN [20], PSyCo [57], ENet-E [33] and RCAN [7].”