Article
Version 1
Preserved in Portico This version is not peer-reviewed
PEIPNet: Parametric Efficient Image-Inpainting Network with Depthwise and Pointwise Convolution
Version 1
: Received: 31 August 2023 / Approved: 1 September 2023 / Online: 5 September 2023 (09:11:57 CEST)
A peer-reviewed article of this Preprint also exists.
Ko, J.; Choi, W.; Lee, S. PEIPNet: Parametric Efficient Image-Inpainting Network with Depthwise and Pointwise Convolution. Sensors 2023, 23, 8313. Ko, J.; Choi, W.; Lee, S. PEIPNet: Parametric Efficient Image-Inpainting Network with Depthwise and Pointwise Convolution. Sensors 2023, 23, 8313.
Abstract
Research on image-inpainting tasks has mainly focused on enhancing performance by augmenting various stages and modules. However, this trend does not consider the increase in the number of model parameters and operational memory, which increases the burden on computational resources. To solve this problem, we propose a Parametric Efficient Image InPainting Network (PEIPNet) for efficient and effective image-inpainting. Unlike other state-of-the-art methods, the proposed model has a one-stage inpainting framework in which depthwise and pointwise convolutions are adopted to reduce the number of parameters and computational costs. To generate semantically appealing results, we selected three unique components: spatially-adaptive denormalization (SPADE), dense dilated convolution module (DDCM), and efficient self-attention (ESA). The SPADE was adopted to conditionally normalize activations according to the mask to distinguish between damaged and undamaged regions. The DDCM was employed at every scale to overcome the gradient-vanishing obstacle and gradually fill-in pixels by capturing global information along the feature maps. The ESA was utilized to obtain clues from unmasked areas by extracting long-range information. In terms of efficiency, our model has the lowest operational memory compared with other state-of-the-art methods. Both qualitative and quantitative experiments demonstrate the generalized inpainting of our method on three public datasets: Paris StreetView, CelebA, and Places2.
Keywords
image inpainting; generative adversarial networks (GANs); lightweight architecture; conditional normalization; dilated convolution; dense block; self-attention
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment