• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >RUNet: A Robust UNet Architecture for Image Super-Resolution
【24h】

RUNet: A Robust UNet Architecture for Image Super-Resolution

机译：卷发：用于图像超分辨率的强大的UNET架构

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Single image super-resolution (SISR) is a challenging ill-posed problem which aims to restore or infer a high-resolution image from a low-resolution one. Powerful deep learning-based techniques have achieved state-of-the-art performance in SISR; however, they can underperform when handling images with non-stationary degradations, such as for the application of projector resolution enhancement. In this paper, a new UNet architecture that is able to learn the relationship between a set of degraded low-resolution images and their corresponding original high-resolution images is proposed. We propose employing a degradation model on training images in a non-stationary way, allowing the construction of a robust UNet (RUNet) for image super-resolution (SR). Experimental results show that the proposed RUNet improves the visual quality of the obtained super-resolution images while maintaining a low reconstruction error.
机译：单图像超分辨率（SISR）是一个具有挑战性的不良问题，其旨在恢复或推断从低分辨率恢复的高分辨率图像。基于强大的深度学习技术在SISR中取得了最先进的表现;但是，当处理具有非静止降级的图像时，它们可以效率低于，例如用于应用投影机分辨率的增强。在本文中，提出了一种能够学习一组降级的低分辨率图像与其对应的原始高分辨率图像之间的关系的新的UNET架构。我们提出以非静止方式在训练图像上采用退化模型，允许构建用于图像超分辨率（SR）的鲁棒UNET（卷卷）。实验结果表明，所提出的卷卷改善了所获得的超分辨率图像的视觉质量，同时保持低重建误差。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号