Skip to main content

Context-Aware Semantic Inpainting.

Li, H., Li, G., Lin, L., Yu, H. and Yu, Y., 2019. Context-Aware Semantic Inpainting. IEEE Transactions on Cybernetics, 49 (12), 4398-4411.

Full text available as:

08493595.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.


DOI: 10.1109/TCYB.2018.2865036


IEEE In recent times, image inpainting has witnessed rapid progress due to the generative adversarial networks (GANs) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder architecture with a fully connected layer, which cannot accurately maintain spatial information. In addition, the discriminator in existing GANs struggles to comprehend high-level semantics within the image context and yields semantically consistent content. Existing evaluation criteria are biased toward blurry results and cannot well characterize edge preservation and visual authenticity in the inpainting results. In this paper, we propose an improved GAN to overcome the aforementioned limitations. Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context. Furthermore, we also introduce two novel measures to better assess the quality of image inpainting results. The experimental results demonstrate that our method outperforms the state-of-the-art under a wide range of criteria.

Item Type:Article
Group:Faculty of Media & Communication
ID Code:31428
Deposited By: Symplectic RT2
Deposited On:06 Nov 2018 14:42
Last Modified:14 Mar 2022 14:13


Downloads per month over past year

More statistics for this item...
Repository Staff Only -