Context-Aware Semantic Inpainting
By Haofeng Li, Guanbin Li, Liang Lin, Yizhou Yu. 2017
52 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Xianglong Liu
- Dacheng Tao
- Sung-Jea Ko
- Shihao Bai
- Aishan Liu
- Edwin R. Hancock
- Seung Park
- Seung-Wook Kim
Citations in the corpus
- Regionwise Generative Adversarial Image Inpainting for Large Missing Areas (2019, background): “It has been widely applied in many scenarios [1]–[3], such as image recovery (removing photograph scratches and text occlusions), photograph editing (removing unwanted objects, face editing), image encoding and transmission (loss of blocky image content caused by network packet loss during image tra”
- PEPSI : Fast Image Inpainting With Parallel Decoding Network (2019, methodology): “Image inpainting techniques have been widely re-searched [1–3, 5, 6, 10, 13, 16, 17, 19, 21, 25, 26, 28] for removing an unwanted object or synthesizing missing parts of an image in various applications such as photo editing, image-based rendering, and computational photography [15, 20, 28].”