• Corpus ID: 13890001

Neural Photo Editing with Introspective Adversarial Networks

  title={Neural Photo Editing with Introspective Adversarial Networks},
  author={Andrew Brock and Theodore Lim and James M. Ritchie and Nick Weston},
The increasingly photorealistic sample quality of generative image models suggests their feasibility in applications beyond image generation. We present the Neural Photo Editor, an interface that leverages the power of generative neural networks to make large, semantically coherent changes to existing images. To tackle the challenge of achieving accurate reconstructions without loss of feature quality, we introduce the Introspective Adversarial Network, a novel hybridization of the VAE and GAN… 

Figures and Tables from this paper


It is found that applying orthogonal regularization to the generator renders it amenable to a simple “truncation trick,” allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator’s input.

Photoshop 2 . 0 : Generative Adversarial Networks for Photo Editing

In this paper we explore how to use Generative Adversarial Neural Networks (GANs) to generate realistic face images that posses certain desirable facial characteristics. Moreover, we develop a

Large Scale GAN Training for High Fidelity Natural Image Synthesis

It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.

Toward better reconstruction of style images with GANs

This paper introduces a loss that penalizes imperfect latent space reconstruction and integrates it with the Bidirectional GAN framework for encoding and generating style images and shows that this penalty aids in producing a more realistic reconstruction.

Anycost GANs for Interactive Image Synthesis and Editing

This paper trains the Anycost GAN to support elastic resolutions and channels for faster image generation at versatile speeds and develops new encoder training and latent code optimization techniques to encourage consistency between the different sub-generators during image projection.

Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders

A generative autoencoder that provides fast encoding, faithful reconstructions, sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs is presented.

User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks

A novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism that can learn descriptive texture manifolds for large datasets and from raw data such as a collection of high-resolution photos.

A survey of image synthesis and editing with generative adversarial networks

This paper surveys recent GAN papers regarding topics including, but not limited to, texture synthesis, image inpainting, image-to-image translation, and image editing.

Image Manipulation with Perceptual Discriminators

The merits of the new architecture, that is called a perceptual discriminator, embeds the convolutional parts of a pre-trained deep classification network inside the discriminator network, and can be trained on unaligned image datasets, while benefiting from the robustness and efficiency of perceptual losses.

ArtGAN: Artwork synthesis with conditional categorical GANs

The proposed ArtGAN is capable to create realistic artwork, as well as generate compelling real world images that globally look natural with clear shape on CIFAR-10.



Autoencoding beyond pixels using a learned similarity metric

An autoencoder that leverages learned representations to better measure similarities in data space is presented and it is shown that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.

Conditional Image Synthesis with Auxiliary Classifier GANs

A variant of GANs employing label conditioning that results in 128 x 128 resolution image samples exhibiting global coherence is constructed and it is demonstrated that high resolution samples provide class information not present in low resolution samples.

Generative Visual Manipulation on the Natural Image Manifold

This paper proposes to learn the natural image manifold directly from data using a generative adversarial neural network, and defines a class of image editing operations, and constrain their output to lie on that learned manifold at all times.

Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks

This paper introduces a novel concept to augment such generative architectures with semantic annotations, either by manually authoring pixel labels or using existing solutions for semantic segmentation, resulting in a content-aware generative algorithm that offers meaningful control over the outcome.

Improved Techniques for Training GANs

This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.

Generating Images with Perceptual Similarity Metrics based on Deep Networks

A class of loss functions, which are called deep perceptual similarity metrics (DeePSiM), are proposed that compute distances between image features extracted by deep neural networks and better reflects perceptually similarity of images and thus leads to better results.

A Neural Algorithm of Artistic Style

This work introduces an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality and offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery.

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.

Adversarial Feature Learning

Bidirectional Generative Adversarial Networks are proposed as a means of learning the inverse mapping of GANs, and it is demonstrated that the resulting learned feature representation is useful for auxiliary supervised discrimination tasks, competitive with contemporary approaches to unsupervised and self-supervised feature learning.

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.