DeepAI AI Chat
Log In Sign Up

GP-GAN: Towards Realistic High-Resolution Image Blending

by   Huikai Wu, et al.
University of Oxford

Recent advances in generative adversarial networks (GANs) have shown promising potentials in conditional image generation. However, how to generate high-resolution images remains an open problem. In this paper, we aim at generating high-resolution well-blended images given composited copy-and-paste ones, i.e. realistic high-resolution image blending. To achieve this goal, we propose Gaussian-Poisson GAN (GP-GAN), a framework that combines the strengths of classical gradient-based approaches and GANs, which is the first work that explores the capability of GANs in high-resolution image blending task to the best of our knowledge. Particularly, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimisation constrained by the gradient and colour information. Gradient filters can obtain gradient information. For generating the colour information, we propose Blending GAN to learn the mapping between the composited image and the well-blended one. Compared to the alternative methods, our approach can deliver high-resolution, realistic images with fewer bleedings and unpleasant artefacts. Experiments confirm that our approach achieves the state-of-the-art performance on Transient Attributes dataset. A user study on Amazon Mechanical Turk finds that majority of workers are in favour of the proposed approach.


page 1

page 5

page 6

page 7

page 8

page 10

page 12

page 13


MelanoGANs: High Resolution Skin Lesion Synthesis with GANs

Generative Adversarial Networks (GANs) have been successfully used to sy...

Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images

Currently generative adversarial networks (GANs) are rarely applied to m...

Energy-relaxed Wassertein GANs(EnergyWGAN): Towards More Stable and High Resolution Image Generation

Recently, generative adversarial networks (GANs) have achieved great imp...

Generation High resolution 3D model from natural language by Generative Adversarial Network

We present a method of generating high resolution 3D shapes from natural...

Synthesising clinically realistic Chest X-rays using Generative Adversarial Networks

Chest x-rays are one of the most commonly performed medical investigatio...

Manifold-Aware CycleGAN for High Resolution Structural-to-DTI Synthesis

Unpaired image-to-image translation has been applied successfully to nat...

On GANs and GMMs

A longstanding problem in machine learning is to find unsupervised metho...