• Corpus ID: 239049868

Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models

  title={Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models},
  author={Rui Ma and Johnathan Czernik and Xian Du},
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these methods only learn the inverse process of the predetermined operation, so they fail to super resolve the real-world LR images; the true formulation deviates from the predetermined operation. To address this problem, we propose a novel supervised method to… 

Figures and Tables from this paper


Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model
This paper builds a real-world super-resolution (RealSR) dataset where paired LR-HR images on the same scene are captured by adjusting the focal length of a digital camera and presents a Laplacian pyramid based kernel prediction network (LP-KPN), which efficiently learns per-pixel kernels to recover the HR image.
Toward Real-World Super-Resolution via Adaptive Downsampling Models
A novel method to simulate an unknown real downsampling process without imposing restrictive prior knowledge is proposed and an effective and generalizable low-frequency loss (LFL) in the adversarial training framework is designed to imitate the distribution of target LR images without using any paired examples.
Blind Super-Resolution Kernel Estimation using an Internal-GAN
KernelGAN is introduced, an image-specific Internal-GAN, which trains solely on the LR test image at test time, and learns its internal distribution of patches, and leads to state-of-the-art results in Blind-SR when plugged into existing SR algorithms.
Kernel Modeling Super-Resolution on Real Low-Resolution Images
The proposed KMSR consists of two stages: a pool of realistic blur-kernels with a generative adversarial network (GAN) and then a super-resolution network with HR and corresponding LR images constructed with the generated kernels that incorporates blur-kernel modeling in the training.
Unpaired Image Super-Resolution Using Pseudo-Supervision
  • S. Maeda
  • Computer Science, Engineering
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
An unpaired SR method using a generative adversarial network that does not require a paired/aligned training dataset is proposed and experiments show that the proposed method is superior to existing solutions to the unpairedSR problem.
Unsupervised Degradation Representation Learning for Blind Super-Resolution
This paper proposes an unsupervised degradation representation learning scheme for blind SR without explicit degradation estimation, and introduces a Degradation-Aware SR (DASR) network with flexible adaption to various degradations based on the learned representations.
Blind Super-Resolution With Iterative Kernel Correction
An iterative correction scheme -- IKC that achieves better results than direct kernel estimation in blind SR problem and an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
  • K. Zhang, W. Zuo, Lei Zhang
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
Extensive experimental results show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
To learn image super-resolution, use a GAN to learn how to do image degradation first
A two-stage process which firstly trains a High-to-Low Generative Adversarial Network to learn how to degrade and downsample high-resolution images requiring, during training, only unpaired high and low- Resolution images can be used to effectively increase the quality of real-world low- resolution images.