Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

PEPSI++: Fast and Lightweight Network for Image Inpainting

Authors
Shin, Y.-G.Sagong, M.-C.Yeo, Y.-J.Kim, S.-W.Ko, S.-J.
Issue Date
1월-2021
Publisher
Institute of Electrical and Electronics Engineers Inc.
Keywords
Deep learning; generative adversarial network (GAN); image inpainting
Citation
IEEE Transactions on Neural Networks and Learning Systems, v.32, no.1, pp.252 - 265
Indexed
SCIE
SCOPUS
Journal Title
IEEE Transactions on Neural Networks and Learning Systems
Volume
32
Number
1
Start Page
252
End Page
265
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/49393
DOI
10.1109/TNNLS.2020.2978501
ISSN
2162-237X
Abstract
Among the various generative adversarial network (GAN)-based image inpainting methods, a coarse-to-fine network with a contextual attention module (CAM) has shown remarkable performance. However, due to two stacked generative networks, the coarse-to-fine network needs numerous computational resources, such as convolution operations and network parameters, which result in low speed. To address this problem, we propose a novel network architecture called parallel extended-decoder path for semantic inpainting (PEPSI) network, which aims at reducing the hardware costs and improving the inpainting performance. PEPSI consists of a single shared encoding network and parallel decoding networks called coarse and inpainting paths. The coarse path produces a preliminary inpainting result to train the encoding network for the prediction of features for the CAM. Simultaneously, the inpainting path generates higher inpainting quality using the refined features reconstructed via the CAM. In addition, we propose Diet-PEPSI that significantly reduces the network parameters while maintaining the performance. In Diet-PEPSI, to capture the global contextual information with low hardware costs, we propose novel rate-adaptive dilated convolutional layers that employ the common weights but produce dynamic features depending on the given dilation rates. Extensive experiments comparing the performance with state-of-the-art image inpainting methods demonstrate that both PEPSI and Diet-PEPSI improve the qualitative scores, i.e., the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), as well as significantly reduce hardware costs, such as computational time and the number of network parameters. © 2012 IEEE.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE