Jointly Optimized Regressors for Image Super‐resolution

By Dengxin Dai, Radu Timofte, Luc Van Gool. 2015

165 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, background): “[5] the authors learn a multitude of patch-specific regressors during training and select the most appropriate regressors for a given LR patch during testing using kNN.”
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, methodology): “Recent popular SISR methods can be classified into edge-based [35], image statisticsbased [9, 18, 46, 12] and patch-based [2, 43, 52, 13, 54, 40, 5] methods.”
Image Super-Resolution Using Deep Convolutional Networks (2014, methodology): “These methods either exploit internal similarities of the same image [5], [13], [16], [19], [47], or learn mapping functions from external low- and high-resolution exemplar pairs [2], [4], [6], [15], [23], [25], [37], [41], [42], [47], [48], [50], [51].”
NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study (2017, background): “We mention also LIVE1 [41, 53], L20 [49, 27], ImageNet [38], Kodak 7 or SuperTex136 [8] that are less popular for single-image SR.”
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network (2018, background): “The work in [9] learned a multitude of patch-specific regressors and proposed to use the most appropriate regressors during testing.”
Fast and accurate image upscaling with super-resolution forests (2015, methodology): “We do not include the results of [11] as they are slightly worse than A+ [31].”
A Deep Convolutional Neural Network with Selection Units for Super-Resolution (2017, methodology): “Jointly optimized regressors (JOR) [4] method employs an expectation-maximization algorithm with tree to learn and apply the best linear mappings to LR patches.”
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results (2020, background): “search topic for decades [33, 17, 56, 65, 63, 69, 70, 71, 61, 13, 28, 64, 14, 15, 38, 40, 43, 16, 2, 3, 26, 29, 21] due to its many applications.”
Seven Ways to Improve Example-Based Single Image Super Resolution (2015, methodology): “To address this problem, the SR literature proposes interpolation-based methods [29], reconstruction-based methods [3, 15, 25, 39, 41], and learning-based methods [18, 10, 30, 31, 7, 5, 42, 6].”