Dual-reference Training Data Acquisition and CNN Construction for Image Super-Resolution

• URL: http://arxiv.org/abs/2108.02348v1
• Date: Thu, 5 Aug 2021 03:31:50 GMT
• Title: Dual-reference Training Data Acquisition and CNN Construction for Image Super-Resolution
• Authors: Yanhui Guo, Xiao Shu, Xiaolin Wu
• Abstract summary: We propose a novel method to capture a large set of realistic LR$sim$HR image pairs using real cameras. Our innovation is to shoot images displayed on an ultra-high quality screen at different resolutions. Experimental results show that training a super-resolution CNN by our LR$sim$HR dataset has superior restoration performance than training it by existing datasets on real world images.
• Score: 33.388234549922025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For deep learning methods of image super-resolution, the most critical issue is whether the paired low and high resolution images for training accurately reflect the sampling process of real cameras. Low and high resolution (LR$\sim$HR) image pairs synthesized by existing degradation models (\eg, bicubic downsampling) deviate from those in reality; thus the super-resolution CNN trained by these synthesized LR$\sim$HR image pairs does not perform well when being applied to real images. In this paper, we propose a novel method to capture a large set of realistic LR$\sim$HR image pairs using real cameras.The data acquisition is carried out under controllable lab conditions with minimum human intervention and at high throughput (about 500 image pairs per hour). The high level of automation makes it easy to produce a set of real LR$\sim$HR training image pairs for each camera. Our innovation is to shoot images displayed on an ultra-high quality screen at different resolutions.There are three distinctive advantages with our method that allow us to collect high-quality training datasets for image super-resolution. First, as the LR and HR images are taken of a 3D planar surface (the screen) the registration problem fits exactly to a homography model. Second, we can display special markers on the image margin to further improve the registration precision.Third, the displayed digital image file can be exploited as a reference to optimize the high frequency content of the restored image. Experimental results show that training a super-resolution CNN by our LR$\sim$HR dataset has superior restoration performance than training it by existing datasets on real world images at the inference stage.

Related papers

• Rethinking Image Super-Resolution from Training Data Perspectives [54.28824316574355]
  We investigate the understudied effect of the training data used for image super-resolution (SR) With this, we propose an automated image evaluation pipeline. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance.
  arXiv  Detail & Related papers  (2024-09-01T16:25:04Z)
• Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction [62.955327005837475]
  Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
  arXiv  Detail & Related papers  (2023-10-29T13:58:57Z)
• Human Guided Ground-truth Generation for Realistic Image Super-resolution [27.74022069080442]
  How to generate the ground-truth (GT) image is a critical issue for training realistic image super-resolution (Real-ISR) models. Existing methods mostly take a set of high-resolution (HR) images as GTs and apply various degradations to simulate their low-resolution (LR) counterparts. We propose a human guided GT generation scheme.
  arXiv  Detail & Related papers  (2023-03-23T06:53:14Z)
• Real-Time Super-Resolution for Real-World Images on Mobile Devices [11.632812550056173]
  Image Super-Resolution (ISR) aims at recovering High-Resolution (HR) images from the corresponding Low-Resolution (LR) counterparts. Recent progress in ISR has been remarkable, but they are way too computationally intensive to be deployed on edge devices. In this work, an approach for real-time ISR on mobile devices is presented, which is able to deal with a wide range of degradations in real-world scenarios.
  arXiv  Detail & Related papers  (2022-06-03T18:44:53Z)
• Exploiting Raw Images for Real-Scene Super-Resolution [105.18021110372133]
  We study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images. We propose a method to generate more realistic training data by mimicking the imaging process of digital cameras. We also develop a two-branch convolutional neural network to exploit the radiance information originally-recorded in raw images.
  arXiv  Detail & Related papers  (2021-02-02T16:10:15Z)
• Joint Generative Learning and Super-Resolution For Real-World Camera-Screen Degradation [6.14297871633911]
  In real-world single image super-resolution (SISR) task, the low-resolution image suffers more complicated degradations. In this paper, we focus on the camera-screen degradation and build a real-world dataset (Cam-ScreenSR) We propose a joint two-stage model. Firstly, the downsampling degradation GAN(DD-GAN) is trained to model the degradation and produces more various of LR images. Then the dual residual channel attention network (DuRCAN) learns to recover the SR image.
  arXiv  Detail & Related papers  (2020-08-01T07:10:13Z)
• Benefiting from Bicubically Down-Sampled Images for Learning Real-World Image Super-Resolution [22.339751911637077]
  We propose to handle real-world SR by splitting this ill-posed problem into two comparatively more well-posed steps. First, we train a network to transform real LR images to the space of bicubically downsampled images in a supervised manner. Second, we take a generic SR network trained on bicubically downsampled images to super-resolve the transformed LR image.
  arXiv  Detail & Related papers  (2020-07-06T20:27:58Z)
• Robust Single-Image Super-Resolution via CNNs and TV-TV Minimization [7.538482310185135]
  Single-image super-resolution is the process of increasing the resolution of an image, obtaining a high-resolution (HR) image from a low-resolution (LR) one. By leveraging large training datasets, convolutional neural networks (CNNs) currently achieve the state-of-the-art performance in this task. We propose to post-process the CNN outputs with an optimization problem that we call TV-TV minimization, which enforces consistency.
  arXiv  Detail & Related papers  (2020-04-02T07:06:55Z)
• Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution [73.86924594746884]
  Deep neural networks have exhibited promising performance in image super-resolution. These networks learn a nonlinear mapping function from low-resolution (LR) images to high-resolution (HR) images. We propose a dual regression scheme by introducing an additional constraint on LR data to reduce the space of the possible functions.
  arXiv  Detail & Related papers  (2020-03-16T04:23:42Z)
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [77.32079593577821]
  PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
  arXiv  Detail & Related papers  (2020-03-08T16:44:31Z)
• Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation [91.40265983636839]
  We propose a framework to learn SR from an arbitrary set of unpaired LR and HR images. We minimize the discrepancy between the generated data and real data while learning a degradation adaptive SR network. The proposed unpaired method achieves state-of-the-art SR results on real-world images, even in the datasets that favor the paired-learning methods more.
  arXiv  Detail & Related papers  (2020-01-08T05:17:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.