基于轻量级GAN的实时视频图像去模糊模型
作者:
作者单位:

作者简介:

通讯作者:

基金项目:

山西省重点研发计划(重点)高新领域项目(201703D111027); 山西省重点研发计划(201803D121048, 201803D121055)


Real-Time Video Image Deblurring Model Based on Lightweight GAN
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    由于手持拍摄设备抖动或目标运动等原因, 使得视频图像资料产生运动模糊问题, 降低了人类的感知质量. 针对该问题从原来如何处理得到清晰图像, 到现在如何高效快捷的获得清晰图像, 提出了一种基于轻量级GAN(Generative Adversarial Network) 的实时视频图像去模糊新模型. 该模型通过定义PatchGAN作为判别网络, 并在其基础上设置了全局图像和局部特征的双尺度判别器; 生成网络以轻量级MobileNetV3为主干网并引入特征金字塔进行特征提取, 以解决判别网络中特征信息利用率低以及生成网络推理效率慢的问题. 该模型采用端到端的方式对视频图像进行快速高效去模糊. 经过在GoPro和Kohler数据集上进行实验, 结果表明该模型去模糊后的锐利图像具有较高的峰值信噪比和结构相似度, 同时比其他模型的推理速度提高了1.7–127倍.

    Abstract:

    Due to the shaking of a handheld camera or the movement of targets, the video image data is subject to motion blur, which reduces the image quality of human perception. With regard to the problem, from how to obtain clear images from the original process to how to obtain clear images efficiently, a new model for real-time video image deblurring based on the lightweight Generative Adversarial Network (GAN) is proposed in this study. The model defines PatchGAN as a discriminant network and sets up a dual-scale discriminator for global images and local features on the basis of it; the generation network takes lightweight MobileNetV3 as the backbone network and introduces a feature pyramid for feature extraction to solve the problem of low utilization of feature information in the discrimination network and low inference efficiency of the generation network. This model uses an end-to-end approach to efficiently deblur the video image. After experiments on the GoPro and Kohler datasets, the results show that the sharp image deblurred by this model has a high peak signal-to-noise ratio and great structural similarity, and the inference speed reaches 1.7–127 times faster than that of other models.

    参考文献
    相似文献
    引证文献
引用本文

贾凡,张英俊,谢斌红.基于轻量级GAN的实时视频图像去模糊模型.计算机系统应用,2021,30(10):31-39

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2020-12-24
  • 最后修改日期:2021-01-25
  • 录用日期:
  • 在线发布日期: 2021-10-08
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号