Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

• URL: http://arxiv.org/abs/2205.03524v1
• Date: Sat, 7 May 2022 02:55:39 GMT
• Title: Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution
• Authors: Xiaoqian Xu, Pengxu Wei, Weikai Chen, Mingzhi Mao, Liang Lin, Guanbin Li
• Abstract summary: Super-resolution (SR) models trained on images from different devices could exhibit distinct imaging patterns. We propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA) We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches.
• Score: 114.26933742226115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on images from different devices. In this paper, we investigate a novel and practical task coded cross-device SR, which strives to adapt a real-world SR model trained on the paired images captured by one camera to low-resolution (LR) images captured by arbitrary target devices. The proposed task is highly challenging due to the absence of paired data from various imaging devices. To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera. DADA employs the Domain-Invariant Attention (DIA) module to establish the basis of target model training even without HR supervision. Furthermore, the dual framework of DADA facilitates an Inter-domain Adversarial Adaptation (InterAA) in one branch for two LR input images from two domains, and an Intra-domain Adversarial Adaptation (IntraAA) in two branches for an LR input image. InterAA and IntraAA together improve the model transferability from the source domain to the target. We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches. We also evaluate the proposed DADA to address the adaptation to the video camera, which presents a promising research topic to promote the wide applications of real-world super-resolution. Our source code is publicly available at https://github.com/lonelyhope/DADA.git.

Related papers

• Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations [61.448005005426666]
  We consider two challenging issues in reference-based super-resolution (RefSR) for smartphone. We propose a novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms.
  arXiv  Detail & Related papers  (2024-05-03T15:20:30Z)
• TransY-Net:Learning Fully Transformer Networks for Change Detection of Remote Sensing Images [64.63004710817239]
  We propose a novel Transformer-based learning framework named TransY-Net for remote sensing image CD. It improves the feature extraction from a global view and combines multi-level visual features in a pyramid manner. Our proposed method achieves a new state-of-the-art performance on four optical and two SAR image CD benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T07:42:19Z)
• Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection [7.064953237013352]
  Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data. We propose a novel and effective four-step UDA approach that leverages self-supervision and trains source and target data concurrently. Our approach achieves state-of-the-art performance, improving upon the nearest competitor by more than 2% in terms of mean Average Precision (mAP)
  arXiv  Detail & Related papers  (2023-08-29T14:48:29Z)
• Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network [14.898170534545727]
  We propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adrial Network (UBCDTLGAN) First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world image domain. Second, the SESRN has the ability to super-resolve the approximated real-like LR image to a photo-realistic HR image.
  arXiv  Detail & Related papers  (2022-11-19T02:19:21Z)
• Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations [66.09210030518686]
  We present a novel self-supervised learning approach for real-world RefSR from observations at dual camera zooms (SelfDZSR) For the first issue, the more zoomed (telephoto) image can be naturally leveraged as the reference to guide the SR of the lesser zoomed (short-focus) image. For the second issue, SelfDZSR learns a deep network to obtain the SR result of short-focal image and with the same resolution as the telephoto image.
  arXiv  Detail & Related papers  (2022-03-02T13:30:56Z)
• Dual-Camera Super-Resolution with Aligned Attention Modules [56.54073689003269]
  We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR) Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy.
  arXiv  Detail & Related papers  (2021-09-03T07:17:31Z)
• Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar [42.78574493628936]
  We develop a Domain-Aware Pyramid-based Face Super-Resolution network, named DAP-FSR network. Our DAP-FSR is the first attempt to super-resolve LR faces from a target domain by exploiting only a pair of high-resolution (HR) and LR exemplars in the target domain. By iteratively updating the latent representations and our decoder, our DAP-FSR will be adapted to the target domain.
  arXiv  Detail & Related papers  (2021-03-16T05:47:26Z)
• 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.