How Real is Real: Evaluating the Robustness of Real-World Super Resolution

• URL: http://arxiv.org/abs/2210.12523v1
• Date: Sat, 22 Oct 2022 18:53:45 GMT
• Title: How Real is Real: Evaluating the Robustness of Real-World Super Resolution
• Authors: Athiya Deviyani, Efe Sinan Hoplamaz, Alan Savio Paul
• Abstract summary: Super-resolution is a well-known problem as most methods rely on the downsampling method performed on the high-resolution image to form the low-resolution image to be known. We will evaluate multiple state-of-the-art super-resolution methods and gauge their performance when presented with various types of real-life images. We will present a potential solution to alleviate the generalization problem which is imminent in most state-of-the-art super-resolution models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image super-resolution (SR) is a field in computer vision that focuses on reconstructing high-resolution images from the respective low-resolution image. However, super-resolution is a well-known ill-posed problem as most methods rely on the downsampling method performed on the high-resolution image to form the low-resolution image to be known. Unfortunately, this is not something that is available in real-life super-resolution applications such as increasing the quality of a photo taken on a mobile phone. In this paper we will evaluate multiple state-of-the-art super-resolution methods and gauge their performance when presented with various types of real-life images and discuss the benefits and drawbacks of each method. We also introduce a novel dataset, WideRealSR, containing real images from a wide variety of sources. Finally, through careful experimentation and evaluation, we will present a potential solution to alleviate the generalization problem which is imminent in most state-of-the-art super-resolution models.

Related papers

• High-Resolution Be Aware! Improving the Self-Supervised Real-World Super-Resolution [37.546746047196486]
  Self-supervised learning is crucial for super-resolution because ground-truth images are usually unavailable for real-world settings. Existing methods derive self-supervision from low-resolution images by creating pseudo-pairs or by enforcing a low-resolution reconstruction objective. This paper strengthens awareness of the high-resolution image to improve the self-supervised real-world super-resolution.
  arXiv  Detail & Related papers  (2024-11-25T08:13:32Z)
• Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution [81.74583887661794]
  We build a new real-world super-resolution benchmark with both integer and non-integer scaling factors. We propose a Dual-level Deformable Implicit Representation (DDIR) to solve real-world scale arbitrary super-resolution. Our trained model achieves state-of-the-art performance on the RealArbiSR and RealSR benchmarks for real-world scale arbitrary super-resolution.
  arXiv  Detail & Related papers  (2024-03-16T13:44:42Z)
• Learning from Multi-Perception Features for Real-Word Image Super-resolution [87.71135803794519]
  We propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information. We also introduce a contrastive regularization term (CR) that improves the model's learning capability.
  arXiv  Detail & Related papers  (2023-05-26T07:35:49Z)
• Multi-Modality Image Super-Resolution using Generative Adversarial Networks [0.0]
  We propose a solution to the joint problem of image super-resolution and multi-modality image-to-image translation. The problem can be stated as the recovery of a high-resolution image in a modality, given a low-resolution observation of the same image in an alternative modality.
  arXiv  Detail & Related papers  (2022-06-18T12:19:31Z)
• Semi-Supervised Super-Resolution [30.872605139672086]
  Super-Resolution is the technique to improve the quality of a low-resolution photo by boosting its plausible resolution. Previous Super-Resolution methods require vast amounts of data for training which becomes problematic in domains where very few low-resolution, high-resolution pairs might be available. This paper introduces a semi-supervised way to perform super-resolution that can generate sharp, high-resolution images with as few as 500 paired examples.
  arXiv  Detail & Related papers  (2022-04-18T07:10:29Z)
• 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos [107.36352212367179]
  We propose RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. We extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input.
  arXiv  Detail & Related papers  (2021-03-11T06:52:12Z)
• A Generative Model for Hallucinating Diverse Versions of Super Resolution Images [0.3222802562733786]
  We are tackling in this work the problem of obtaining different high-resolution versions from the same low-resolution image using Generative Adversarial Models. Our learning approach makes use of high frequencies available in the training high-resolution images for preserving and exploring in an unsupervised manner.
  arXiv  Detail & Related papers  (2021-02-12T17:11:42Z)
• Deep Learning-based Face Super-resolution: A Survey [78.11274281686246]
  Face super-resolution, also known as face hallucination, is a domain-specific image super-resolution problem. To date, few summaries of the studies on the deep learning-based face super-resolution are available. In this survey, we present a comprehensive review of deep learning techniques in face super-resolution in a systematic manner.
  arXiv  Detail & Related papers  (2021-01-11T08:17:11Z)
• Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping [6.302374268077337]
  We argue that, first and foremost, the problem of SISR is an one-to-many mapping problem between the low-resolution and all possible candidate high-resolution images. We propose a model that learns how to transform high-resolution images to low-resolution images that resemble realistically taken low-resolution photos.
  arXiv  Detail & Related papers  (2020-06-21T04:14:24Z)
• Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder [47.53609520395504]
  We revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution. We propose a joint image denoising and super-resolution model via Variational AutoEncoder. With the aid of the discriminator, an additional overhead of super-resolution subnetwork is attached to super-resolve the denoised image with photo-realistic visual quality.
  arXiv  Detail & Related papers  (2020-04-27T13:49:36Z)
• 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)

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.