The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks

• URL: http://arxiv.org/abs/2211.05018v1
• Date: Wed, 9 Nov 2022 16:49:35 GMT
• Title: The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks
• Authors: Matthew Aquilina, Keith George Ciantar, Christian Galea, Kenneth P. Camilleri, Reuben A. Farrugia, John Abela
• Abstract summary: We present a framework for combining blind SR prediction mechanism with any deep SR network. We show that our hybrid models consistently achieve stronger SR performance than both their non-blind and blind counterparts.
• Score: 14.804000317612305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To date, the best-performing blind super-resolution (SR) techniques follow one of two paradigms: A) generate and train a standard SR network on synthetic low-resolution - high-resolution (LR - HR) pairs or B) attempt to predict the degradations an LR image has suffered and use these to inform a customised SR network. Despite significant progress, subscribers to the former miss out on useful degradation information that could be used to improve the SR process. On the other hand, followers of the latter rely on weaker SR networks, which are significantly outperformed by the latest architectural advancements. In this work, we present a framework for combining any blind SR prediction mechanism with any deep SR network, using a metadata insertion block to insert prediction vectors into SR network feature maps. Through comprehensive testing, we prove that state-of-the-art contrastive and iterative prediction schemes can be successfully combined with high-performance SR networks such as RCAN and HAN within our framework. We show that our hybrid models consistently achieve stronger SR performance than both their non-blind and blind counterparts. Furthermore, we demonstrate our framework's robustness by predicting degradations and super-resolving images from a complex pipeline of blurring, noise and compression.

Related papers

• ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution [60.90817228730133]
  Single image super-resolution (SISR) is a challenging problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart. Recent approaches are trained on simulated LR images degraded by simplified down-sampling operators. We propose a novel Invertible scale-Conditional Function (ICF) which can scale an input image and then restore the original input with different scale conditions.
  arXiv  Detail & Related papers  (2023-07-24T12:42:45Z)
• Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images [16.497489431525565]
  This paper proposes crack segmentation augmented by super resolution (SR) with deep neural networks. A SR network is jointly trained with a binary segmentation network in an end-to-end manner. For realistic scenarios, the SR network is extended from non-blind to blind for processing a low-resolution image degraded by unknown blurs.
  arXiv  Detail & Related papers  (2023-02-24T07:17:15Z)
• Learning Detail-Structure Alternative Optimization for Blind Super-Resolution [69.11604249813304]
  We propose an effective and kernel-free network, namely DSSR, which enables recurrent detail-structure alternative optimization without blur kernel prior incorporation for blind SR. In our DSSR, a detail-structure modulation module (DSMM) is built to exploit the interaction and collaboration of image details and structures. Our method achieves the state-of-the-art against existing methods.
  arXiv  Detail & Related papers  (2022-12-03T14:44:17Z)
• Degradation-Guided Meta-Restoration Network for Blind Super-Resolution [45.61951760826198]
  Blind super-resolution (SR) aims to recover high-quality visual textures from a low-resolution (LR) image. Existing SR approaches either assume a predefined blur kernel or a fixed noise, which limits these approaches in challenging cases. We propose a Degradation-guided Meta-restoration network for blind Super-Resolution (DMSR) that facilitates image restoration for real cases.
  arXiv  Detail & Related papers  (2022-07-03T03:24:45Z)
• Improving Super-Resolution Performance using Meta-Attention Layers [17.870338228921327]
  Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. Ill-posed nature of SR can make it difficult to accurately super-resolve an image which has undergone multiple different degradations. We introduce meta-attention, a mechanism which allows any SR CNN to exploit the information available in relevant degradation parameters.
  arXiv  Detail & Related papers  (2021-10-27T09:20:21Z)
• Structure-Preserving Image Super-Resolution [94.16949589128296]
  Structures matter in single image super-resolution (SISR) Recent studies have promoted the development of SISR by recovering photo-realistic images. However, there are still undesired structural distortions in the recovered images.
  arXiv  Detail & Related papers  (2021-09-26T08:48:27Z)
• DynaVSR: Dynamic Adaptive Blind Video Super-Resolution [60.154204107453914]
  DynaVSR is a novel meta-learning-based framework for real-world video SR. We train a multi-frame downscaling module with various types of synthetic blur kernels, which is seamlessly combined with a video SR network for input-aware adaptation. Experimental results show that DynaVSR consistently improves the performance of the state-of-the-art video SR models by a large margin.
  arXiv  Detail & Related papers  (2020-11-09T15:07:32Z)
• Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution [20.537597542144916]
  We consider a deep cyclic network structure to maintain the domain consistency between the LR and HR data distributions. We propose the Super-Resolution Residual Cyclic Generative Adversarial Network (SRResCycGAN) by training with a generative adversarial network (GAN) framework for the LR to HR domain translation.
  arXiv  Detail & Related papers  (2020-09-07T11:11:18Z)
• Structure-Preserving Super Resolution with Gradient Guidance [87.79271975960764]
  Structures matter in single image super resolution (SISR) Recent studies benefiting from generative adversarial network (GAN) have promoted the development of SISR. However, there are always undesired structural distortions in the recovered images.
  arXiv  Detail & Related papers  (2020-03-29T17:26:58Z)
• DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution [69.2432352477966]
  Real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair.
  arXiv  Detail & Related papers  (2020-02-25T18:24:51Z)

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.