Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published February 28, 2021 | Version v1
Journal article Open

A New Image Completion Method Inserting an Image Generated by Sketch Image

  • 1. Department of Electronics and Communications Eng., Kwangwoon Univ., Seoul, Korea.
  • 2. IACF, Kwangwoon Univ., Seoul, Korea
  • 1. Publisher

Description

Recently, many studies on the image completion methods make us erase obstacles and fill the hole realistically but putting a new object in its place cannot be solved with the existing Image Completion. To solve this problem, this paper proposes Image Completion which filled a new object that is created through sketch image. The proposed network use pix2pix image translation model for generating object image from sketch image. The image completion network used gated convolution to reduce the weight of meaningless pixels in the convolution process. And WGAN-GP loss is used to reduce the mode dropping. In addition, by adding a contextual attention layer in the middle of the network, image completion is performed by referring to the feature value at a distant pixel. To train the models, Places2 dataset was used as background training data for image completion and Standard Dog dataset was used as training data for pix2pix. As a result of the experiment, an image of dog is generated well by sketch image and use this image as an input of the image completion network, it can generate the realistic image as a result.

Files

D84310210421.pdf

Files (603.7 kB)

Name Size Download all
md5:a4f185e7a7e745fa114622f41f135254
603.7 kB Preview Download

Additional details

Related works

Is cited by
Journal article: 2278-3075 (ISSN)

Subjects

ISSN
2278-3075
Retrieval Number
100.1/ijitee.D84310210421