Context-Aware Semantic Inpainting
This work addresses the challenge of generating realistic and semantically consistent content in image inpainting for applications in computer vision and image editing, representing an incremental improvement over existing GAN approaches.
The paper tackles the problem of semantic image inpainting by addressing limitations in existing GAN-based methods, such as poor spatial information maintenance and inadequate high-level semantic understanding, resulting in a proposed improved GAN framework that outperforms state-of-the-art methods across various criteria.
Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) 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 struggle to understand high-level semantics within the image context and yield semantically consistent content. Existing evaluation criteria are biased towards blurry results and cannot well characterize edge preservation and visual authenticity in the inpainting results. In this paper, we propose an improved generative adversarial network 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. Experimental results demonstrate that our method outperforms the state of the art under a wide range of criteria.