Patch-Based Image Inpainting with Generative Adversarial Networks
This work addresses image inpainting for computer vision applications, presenting an incremental improvement over existing network solutions.
The paper tackles the problem of image inpainting over large missing regions by proposing a GAN-based method that combines global and patchGAN architectures to reduce artifacts and noise, achieving considerable improvements in visual and quantitative evaluations compared to state-of-the-art methods.
Area of image inpainting over relatively large missing regions recently advanced substantially through adaptation of dedicated deep neural networks. However, current network solutions still introduce undesired artifacts and noise to the repaired regions. We present an image inpainting method that is based on the celebrated generative adversarial network (GAN) framework. The proposed PGGAN method includes a discriminator network that combines a global GAN (G-GAN) architecture with a patchGAN approach. PGGAN first shares network layers between G-GAN and patchGAN, then splits paths to produce two adversarial losses that feed the generator network in order to capture both local continuity of image texture and pervasive global features in images. The proposed framework is evaluated extensively, and the results including comparison to recent state-of-the-art demonstrate that it achieves considerable improvements on both visual and quantitative evaluations.