A Simple Plugin for Transforming Images to Arbitrary Scales

• URL: http://arxiv.org/abs/2210.03417v1
• Date: Fri, 7 Oct 2022 09:24:38 GMT
• Title: A Simple Plugin for Transforming Images to Arbitrary Scales
• Authors: Qinye Zhou, Ziyi Li, Weidi Xie, Xiaoyun Zhang, Ya Zhang, Yanfeng Wang
• Abstract summary: We develop a general plugin that can be inserted into existing super-resolution models, conveniently augmenting their ability towards Arbitrary Resolution Image Scaling. We show that the resulting models can not only maintain their original performance on fixed scale factor but also extrapolate to unseen scales, substantially outperforming existing any-scale super-resolution models on standard benchmarks.
• Score: 47.36233857830832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing models on super-resolution often specialized for one scale, fundamentally limiting their use in practical scenarios. In this paper, we aim to develop a general plugin that can be inserted into existing super-resolution models, conveniently augmenting their ability towards Arbitrary Resolution Image Scaling, thus termed ARIS. We make the following contributions: (i) we propose a transformer-based plugin module, which uses spatial coordinates as query, iteratively attend the low-resolution image feature through cross-attention, and output visual feature for the queried spatial location, resembling an implicit representation for images; (ii) we introduce a novel self-supervised training scheme, that exploits consistency constraints to effectively augment the model's ability for upsampling images towards unseen scales, i.e. ground-truth high-resolution images are not available; (iii) without loss of generality, we inject the proposed ARIS plugin module into several existing models, namely, IPT, SwinIR, and HAT, showing that the resulting models can not only maintain their original performance on fixed scale factor but also extrapolate to unseen scales, substantially outperforming existing any-scale super-resolution models on standard benchmarks, e.g. Urban100, DIV2K, etc.

Related papers

• $\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model [45.65903826290642]
  ASSR aims to super-resolve low-resolution images to high-resolution images at any scale using a single model. We propose a novel arbitrary-scale super-resolution method, called $textS3$Mamba, to construct a scalable continuous representation space.
  arXiv  Detail & Related papers  (2024-11-16T11:13:02Z)
• Domain Transfer in Latent Space (DTLS) Wins on Image Super-Resolution -- a Non-Denoising Model [13.326634982790528]
  We propose a simple approach which gets away from using Gaussian noise but adopts some basic structures of diffusion models for efficient image super-resolution. Experimental results show that our method outperforms not only state-of-the-art large scale super resolution models, but also the current diffusion models for image super-resolution.
  arXiv  Detail & Related papers  (2023-11-04T09:57:50Z)
• A Unified Conditional Framework for Diffusion-based Image Restoration [39.418415473235235]
  We present a unified conditional framework based on diffusion models for image restoration. We leverage a lightweight UNet to predict initial guidance and the diffusion model to learn the residual of the guidance. To handle high-resolution images, we propose a simple yet effective inter-step patch-splitting strategy.
  arXiv  Detail & Related papers  (2023-05-31T17:22:24Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Implicit Diffusion Models for Continuous Super-Resolution [65.45848137914592]
  This paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution. IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework. The scaling factor regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output.
  arXiv  Detail & Related papers  (2023-03-29T07:02:20Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations [61.95114821573875]
  We introduce Plug-In Inversion, which relies on a simple set of augmentations and does not require excessive hyper- parameter tuning. We illustrate the practicality of our approach by inverting Vision Transformers (ViTs) and Multi-Layer Perceptrons (MLPs) trained on the ImageNet dataset.
  arXiv  Detail & Related papers  (2022-01-31T02:12:45Z)
• 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.