Collaging Class-specific GANs for Semantic Image Synthesis

TL;DR

This paper introduces a novel method for high-resolution semantic image synthesis by combining a base generator with multiple class-specific GANs, enabling detailed object control and improved image quality.

Contribution

It presents a new framework that uses separate class-specific GANs alongside a base generator for enhanced image resolution and object-level manipulation.

Findings

High-quality, high-resolution images generated.

Effective object-level control demonstrated.

Improved image quality over baseline methods.

Abstract

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy manipulation of a specific object in the scene. Experiments show that our approach can generate high quality images in high resolution while having flexibility of object-level control by using class-specific generators.