PEDESTRIAN IMAGE INPAINTING BASED ON GENERATIVE ADVERSARIAL NETWORK ARCHITECTURE

Tongshun Zhang

Abstract


The research of image defect repair aims to automatically repair the defect content in the image through the computer. In recent years, the emergence of deep neural network technology has effectively promoted the development of image restoration technology. This article focuses on the subject of pedestrian image restoration. Today, surveillance cameras have been widely deployed in every corner of the city. Therefore, huge pedestrian images can be acquired every second. Therefore, how to automatically analyze and understand its basic content has become an urgent research topic, which has obvious theoretical and practical value. Obviously, the quality of the source image will seriously affect the subsequent stage of understanding. Therefore, this article will discuss how to recover damaged pedestrian images. In order to recover robustly, we adopted an adversarial generation framework.

Keywords


image inpainting; deep learning; generative adversarial networks; neural networks; computer vision.

Full Text:

PDF

References


Barnes C, Shechtman E, Finkelstein A, et al. PatchMatch[C]// Acm Siggraph. ACM, 2009.

Iizuka S, Simo-Serra E, Ishikawa H. Globally and locally consistent image completion. ACM Transactions on Graphics, 2017, 36(4): 107.

Yu J, Lin Z, Yang J, et al. Generative image inpainting with contextual attention//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, United States, 2018: 5505-5514.

Pathak D, Krahenbuhl P, Donahue J, et al. Context encoders: feature learning by inpainting//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, America, 2016: 2536-2544.

Deng Y, Ping L, Chen CL, Member, IEEE (2015) Learning to recognize pedestrian attribute. Computer Science

Liu G, Reda FA, Shih KJ, Wang TC, Tao A, Catanzaro B (2018) Image inpainting for irregular holes using partial convolutions. In: European Conference on Computer Vision

Guilin Liu, Fitsum A. Reda, Kevin J. Shih, Ting-Chun Wang, Andrew Tao, and Bryan Catanzaro. Image inpainting for irregular holes using partial convolutions. In European Conference on Computer Vision, pages 85–100, 2018.

Chuanxia Zheng, Tat-Jen Cham, and Jianfei Cai. Pluralistic image completion. In IEEE Conference on Computer Vision and Pattern Recognition, 2019.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2019 International Educational Applied Scientific Research Journal