Attention-based Multi-Reference Learning for Image Super-Resolution

• URL: http://arxiv.org/abs/2108.13697v1
• Date: Tue, 31 Aug 2021 09:12:26 GMT
• Title: Attention-based Multi-Reference Learning for Image Super-Resolution
• Authors: Marco Pesavento, Marco Volino and Adrian Hilton
• Abstract summary: This paper proposes a novel Attention-based Multi-Reference Super-resolution network. It learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output. It achieves significantly improved performance over state-of-the-art reference super-resolution approaches.
• Score: 29.361342747786164
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output whilst maintaining spatial coherence. The use of multiple reference images together with attention-based sampling is demonstrated to achieve significantly improved performance over state-of-the-art reference super-resolution approaches on multiple benchmark datasets. Reference super-resolution approaches have recently been proposed to overcome the ill-posed problem of image super-resolution by providing additional information from a high-resolution reference image. Multi-reference super-resolution extends this approach by providing a more diverse pool of image features to overcome the inherent information deficit whilst maintaining memory efficiency. A novel hierarchical attention-based sampling approach is introduced to learn the similarity between low-resolution image features and multiple reference images based on a perceptual loss. Ablation demonstrates the contribution of both multi-reference and hierarchical attention-based sampling to overall performance. Perceptual and quantitative ground-truth evaluation demonstrates significant improvement in performance even when the reference images deviate significantly from the target image. The project website can be found at https://marcopesavento.github.io/AMRSR/

Related papers

• AccDiffusion: An Accurate Method for Higher-Resolution Image Generation [63.53163540340026]
  We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training. An in-depth analysis in this paper reveals an identical text prompt for different patches causes repeated object generation. Our AccDiffusion, for the first time, proposes to decouple the vanilla image-content-aware prompt into a set of patch-content-aware prompts.
  arXiv  Detail & Related papers  (2024-07-15T14:06:29Z)
• Detail-Enhancing Framework for Reference-Based Image Super-Resolution [8.899312174844725]
  We propose a Detail-Enhancing Framework (DEF) for reference-based super-resolution. Our proposed method achieves superior visual results while maintaining comparable numerical outcomes.
  arXiv  Detail & Related papers  (2024-05-01T10:27:22Z)
• LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution [86.81241084950524]
  It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR) Previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. We construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112,142 groups of 300x300 training images, which is 10x of the existing largest RefSR dataset.
  arXiv  Detail & Related papers  (2023-03-09T01:07:06Z)
• 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)
• Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
  This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network. We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
  arXiv  Detail & Related papers  (2022-04-19T17:59:45Z)
• HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars [11.81364643562714]
  We propose an efficient Headshot Image Super-Resolution with Multiple Exemplars network (HIME) method. Compared with previous methods, our network can effectively handle the misalignment between the input and the reference. We also propose a correlation loss that provides a rich representation of the local texture in a controllable spatial range.
  arXiv  Detail & Related papers  (2022-03-28T16:13:28Z)
• Variational AutoEncoder for Reference based Image Super-Resolution [27.459299640768773]
  We propose a reference based image super-resolution, for which any arbitrary image can act as a reference for super-resolution. Even using random map or low-resolution image itself, the proposed RefVAE can transfer the knowledge from the reference to the super-resolved images.
  arXiv  Detail & Related papers  (2021-06-08T04:12:38Z)
• MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution [74.24676600271253]
  We propose the MASA network for RefSR, where two novel modules are designed to address these problems. The proposed Match & Extraction Module significantly reduces the computational cost by a coarse-to-fine correspondence matching scheme. The Spatial Adaptation Module learns the difference of distribution between the LR and Ref images, and remaps the distribution of Ref features to that of LR features in a spatially adaptive way.
  arXiv  Detail & Related papers  (2021-06-04T07:15:32Z)
• Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networks [1.3764085113103222]
  The presented research proposes a novel residual attention model (RAMS) that efficiently tackles the multi-image super-resolution task. We introduce the mechanism of visual feature attention with 3D convolutions in order to obtain an aware data fusion and information extraction. Our representation learning network makes extensive use of nestled residual connections to let flow redundant low-frequency signals.
  arXiv  Detail & Related papers  (2020-07-06T22:54:02Z)
• Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
  convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
  arXiv  Detail & Related papers  (2020-03-15T11:04:30Z)

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.