当前位置: X-MOL 学术Signal Image Video Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A robust and efficient image de-fencing approach using conditional generative adversarial networks
Signal, Image and Video Processing ( IF 2.0 ) Pub Date : 2020-07-30 , DOI: 10.1007/s11760-020-01749-6
Divyanshu Gupta , Shorya Jain , Utkarsh Tripathi , Pratik Chattopadhyay , Lipo Wang

Image de-fencing is one of the most important aspects of recreational photography in which the objective is to remove the fence texture present in an image and generate an aesthetically pleasing version of the same image without the fence texture. In this paper, we present an automated and effective technique for fence removal and image reconstruction using conditional generative adversarial networks (cGANs). These networks have been successfully applied in several other domains of computer vision, focusing on image generation and rendering. Our approach is based on a two-stage architecture involving two cGANs in succession, in which the first cGAN generates the fence mask from an input fenced image, and the next one generates the final de-fenced image from the given input and the corresponding fence mask obtained from the previous cGAN. Training of these networks is carried out independently using suitable loss functions, and during the deployment phase, the above two networks are stacked together in an end-to-end manner to generate the de-fenced image from an unknown test image. Extensive qualitative and quantitative evaluations using challenging data sets emphasize the effectiveness of our approach over state-of-the-art de-fencing techniques. The data sets used in the experiments have also been made available for further comparison.

中文翻译:

一种使用条件生成对抗网络的强大而有效的图像防御方法

图像防护是休闲摄影最重要的方面之一,其目的是去除图像中存在的栅栏纹理,并生成没有栅栏纹理的同一图像的美观版本。在本文中,我们提出了一种使用条件生成对抗网络 (cGAN) 进行栅栏移除和图像重建的自动化有效技术。这些网络已成功应用于计算机视觉的其他几个领域,专注于图像生成和渲染。我们的方法基于一个两阶段架构,涉及两个连续的 cGAN,其中第一个 cGAN 从输入的栅栏图像生成栅栏掩码,下一个从给定的输入和相应的栅栏生成最终的防御图像从之前的 cGAN 获得的掩码。这些网络的训练是使用合适的损失函数独立进行的,在部署阶段,上述两个网络以端到端的方式堆叠在一起,以从未知的测试图像生成防御图像。使用具有挑战性的数据集进行广泛的定性和定量评估强调了我们的方法相对于最先进的防御技术的有效性。实验中使用的数据集也可用于进一步比较。使用具有挑战性的数据集进行广泛的定性和定量评估强调了我们的方法相对于最先进的防御技术的有效性。实验中使用的数据集也可用于进一步比较。使用具有挑战性的数据集进行广泛的定性和定量评估强调了我们的方法相对于最先进的防御技术的有效性。实验中使用的数据集也可用于进一步比较。
更新日期:2020-07-30
down
wechat
bug