PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting

Abstract

The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. But this type of method generally attempts to generate one single "optimal" result, ignoring many other plausible results. Considering the uncertainty of the inpainting task, one sole result can hardly be regarded as a desired regeneration of the missing area. In view of this weakness, which is related to the design of the previous algorithms, we propose a novel deep generative model equipped with a brand new style extractor which can extract the style feature (latent vector) from the ground truth. Once obtained, the extracted style feature and the ground truth are both input into the generator. We also craft a consistency loss that guides the generated image to approximate the ground truth. After iterations, our generator is able to learn the mapping of styles corresponding to multiple sets of vectors. The proposed model can generate a large number of results consistent with the context semantics of the image. Moreover, we evaluated the effectiveness of our model on three datasets, i.e., CelebA, PlantVillage, and MauFlex. Compared to state-of-the-art inpainting methods, this model is able to offer desirable inpainting results with both better quality and higher diversity. The code and model will be made available on https://github.com/vivitsai/PiiGAN.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Toward Multimodal Image-to-Image Translation
• Wasserstein GAN
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
• Image Inpainting via Generative Multi-column Convolutional Neural Networks
• High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks

Cited by in corpus (4)

• Inpainting Galactic Foreground Intensity and Polarization maps using Convolutional Neural Network
• Image Inpainting Using Wasserstein Generative Adversarial Imputation Network
• A New Multiple Max-pooling Integration Module and Cross Multiscale Deconvolution Network Based on Image Semantic Segmentation
• DT-Net: A novel network based on multi-directional integrated convolution and threshold convolution