Patch-Based Image Inpainting with Generative Adversarial Networks

Abstract

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.

References in corpus (1)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Cited by in corpus (17)

• A Systematic Survey of Regularization and Normalization in GANs
• Texture Memory-Augmented Deep Patch-Based Image Inpainting
• Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
• Object Discovery with a Copy-Pasting GAN
• Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties
• Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
• ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image
• Inpainting hydrodynamical maps with deep learning
• Unsupervised Change Detection in Satellite Images with Generative Adversarial Network
• Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
• Hallucinating Beyond Observation: Learning to Complete with Partial Observation and Unpaired Prior Knowledge
• GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences
• Eliminating Shadow Artifacts via Generative Inpainting Networks to Quantify Vascular Changes of the Choroid
• Translate the Facial Regions You Like Using Region-Wise Normalization
• Generative Residual Attention Network for Disease Detection
• Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach
• Pixel-wise Conditioning of Generative Adversarial Networks