A comparative analysis of SRGAN models

• URL: http://arxiv.org/abs/2307.09456v2
• Date: Wed, 19 Jul 2023 14:27:57 GMT
• Title: A comparative analysis of SRGAN models
• Authors: Fatemeh Rezapoor Nikroo, Ajinkya Deshmukh, Anantha Sharma, Adrian Tam, Kaarthik Kumar, Cleo Norris, Aditya Dangi
• Abstract summary: We evaluate the performance of SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images. Some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In this study, we evaluate the performance of multiple state-of-the-art SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images which undergo degradation using a pipeline. Our results show that some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine. We observe that EDSR-BASE model from huggingface outperforms the remaining candidate models in terms of both quantitative metrics and subjective visual quality assessments with least compute overhead. Specifically, EDSR generates images with higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) values and are seen to return high quality OCR results with Tesseract OCR engine. These findings suggest that EDSR is a robust and effective approach for single-image super-resolution and may be particularly well-suited for applications where high-quality visual fidelity is critical and optimized compute.

Related papers

• One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance [32.88048472109016]
  Scene text recognition (STR) from high-resolution (HR) images has been significantly successful, however text reading on low-resolution (LR) images is still challenging. Recently many scene text image super-resolution (STISR) models have been proposed to generate super-resolution (SR) images for the LR ones, then STR is done on the SR images, which thus boosts recognition performance. In this paper, we propose a novel method called IMAGE to effectively recognize and recover LR scene text images simultaneously.
  arXiv  Detail & Related papers  (2024-09-22T15:05:25Z)
• DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution [88.13972071356422]
  We propose a diffusion-style data augmentation scheme for GAN-based image super-resolution (SR) methods, known as DifAugGAN. It involves adapting the diffusion process in generative diffusion models for improving the calibration of the discriminator during training. Our DifAugGAN can be a Plug-and-Play strategy for current GAN-based SISR methods to improve the calibration of the discriminator and thus improve SR performance.
  arXiv  Detail & Related papers  (2023-11-30T12:37:53Z)
• ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution [76.7408734079706]
  Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. We propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure.
  arXiv  Detail & Related papers  (2023-07-26T07:45:14Z)
• Underwater Image Super-Resolution using Generative Adversarial Network-based Model [3.127436744845925]
  Single image super-resolution (SISR) models are able to enhance the resolution and visual quality of underwater images. In this paper, we fine-tune the pre-trained Real-ESRGAN model for underwater image super-resolution.
  arXiv  Detail & Related papers  (2022-11-07T13:38:28Z)
• Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution [64.15915577164894]
  A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing. HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
  arXiv  Detail & Related papers  (2022-06-07T14:55:32Z)
• Textural-Structural Joint Learning for No-Reference Super-Resolution Image Quality Assessment [59.91741119995321]
  We develop a dual stream network to jointly explore the textural and structural information for quality prediction, dubbed TSNet. By mimicking the human vision system (HVS) that pays more attention to the significant areas of the image, we develop the spatial attention mechanism to make the visual-sensitive areas more distinguishable. Experimental results show the proposed TSNet predicts the visual quality more accurate than the state-of-the-art IQA methods, and demonstrates better consistency with the human's perspective.
  arXiv  Detail & Related papers  (2022-05-27T09:20:06Z)
• Generative Adversarial Networks for Image Super-Resolution: A Survey [101.39605080291783]
  Single image super-resolution (SISR) has played an important role in the field of image processing. Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples. In this paper, we conduct a comparative study of GANs from different perspectives.
  arXiv  Detail & Related papers  (2022-04-28T16:35:04Z)
• A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators [0.0]
  Blind image super-resolution(SR) is a long-standing task in CV that aims to restore low-resolution images suffering from unknown and complex distortions. We present A-ESRGAN, a GAN model for blind SR tasks featuring an attention U-Net based, multi-scale discriminator.
  arXiv  Detail & Related papers  (2021-12-19T02:50:23Z)
• Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution [40.350308926790255]
  This paper proposes an unsupervised blind HSI SR method to handle blind HSI fusion problem. We first propose an alternating optimization based deep framework to estimate the degeneration models and reconstruct the latent image. Then, a meta-learning based mechanism is further proposed to pre-train the network, which can effectively improve the speed and generalization ability.
  arXiv  Detail & Related papers  (2020-12-03T07:52:32Z)
• Characteristic Regularisation for Super-Resolving Face Images [81.84939112201377]
  Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery. Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data. This renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution. We formulate a method that joins the advantages of conventional SR and UDA models.
  arXiv  Detail & Related papers  (2019-12-30T16:27:24Z)

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.