A New Image Completion Method Inserting an Image Generated by Sketch Image
Gilhee Choi1, Kyounghak Lee2, Hyung-Hwa Ko3

1Hyung-Hwa Ko, Department of Electronics and Communications Eng, Kwangwoon Univ, Seoul, Korea.
2GilHee Choi, Department of Electronics and Communications Eng, Kwangwoon Univ., Seoul, Korea.
KyoungHak Lee, IACF, Kwangwoon Univ, Seoul, Korea. 
Manuscript received on January 02, 2021. | Revised Manuscript received on January 15, 2021. | Manuscript published on February 28, 2021. | PP: 14-18 | Volume-10 Issue-4, February 2021 | Retrieval Number: 100.1/ijitee.D84310210421| DOI: 10.35940/ijitee.D8431.0210421
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: 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. 
Keywords: Image Completion, Sketch, Pix2pix, WGAN.