Conditioned Regression Models for Non-blind Single Image Super-Resolution

By Gernot Riegler, Samuel Schulter, Matthias Rüther, Horst Bischof. 2015

103 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

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “By further considering that Gaussian kernels sufﬁce for the SISR task, we perform two Gaussian blur operations , i.e ., B iso with isotropic Gaussian kernels and B aniso with anisotropic Gaussian kernels [3, 43, 58].”
Dynamic Neural Networks: A Survey (2021, background): “Image I Object detection (face [38], [181], [182], facial point [183], pedestrian [184], general [31], [185], [186], [187], [188]) Image segmentation [101], [189], Super resolution [190], Style transfer [191], Coarse-to-fine classification [192]”
Dynamic Filter Networks (2016, background): “[17] for single image non-blind single image super resolution.”
Blind Super-Resolution Kernel Estimation using an Internal-GAN (2019, background): “The importance of the SR-kernel accuracy was further analyzed empirically in [27].”
Deep Unfolding Network for Image Super-Resolution (2020, methodology): “To ﬂexibly deal with a blurry LR image, the methods proposed in [44, 67] take the PCA dimension reduced blur kernel as input.”
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (2017, methodology): “, anisotropic Gaussian, which is characterized by a Gaussian probability density function N (0,Σ) with zero mean and varying covariance matrix Σ [38].”
Seven Ways to Improve Example-Based Single Image Super Resolution (2015, result): “Note that generally the explicit form for the degradation operators is unknown and their estimation from prior train examples is imprecise [11, 26], therefore our reported results with (B) refinement are an upper bound for a practical implementation and difficult to reach.”
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising (2017, background): “Similar phenomenon has also been recognized in the task of single image super-resolution (SISR) [47].”
Blind Super-Resolution With Iterative Kernel Correction (2019, methodology): “We compare the SFTMD with the SOTA non-blind SR methods SRCNN-CAB [25] and SRMD [39].”
Flow-based Kernel Prior with Application to Blind Super-Resolution (2021, background): “Since the blur kernels of real LR images are usually unimodal [35, 41] and can typically be modeled by a Gaussian [40], most existing blind SR works [3, 17, 21, 40, 42, 43, 49, 54, 55] assume the SR kernel is isotropic or anisotropic Gaussian kernel.”
Personalized Federated Learning using Hypernetworks (2021, background): “Hypernetworks (HNs) (Klein et al., 2015; Riegler et al., 2015; Ha et al., 2017) are deep neural networks that output the weights of another target network, that performs the learning task.”