Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts

TL;DR

This paper introduces a new deep conditional GAN architecture that generates realistic outdoor scene images conditioned on semantic layouts and scene attributes, effectively capturing diverse conditions like weather and time of day.

Contribution

The work presents a novel GAN architecture that integrates semantic layouts and scene attributes as conditioning variables for outdoor scene image synthesis.

Findings

Successfully generates realistic outdoor scenes with clear object boundaries.

Able to produce images under various conditions such as different weather and lighting.

Demonstrates improved control over scene attributes in generated images.

Abstract

Automatic image synthesis research has been rapidly growing with deep networks getting more and more expressive. In the last couple of years, we have observed images of digits, indoor scenes, birds, chairs, etc. being automatically generated. The expressive power of image generators have also been enhanced by introducing several forms of conditioning variables such as object names, sentences, bounding box and key-point locations. In this work, we propose a novel deep conditional generative adversarial network architecture that takes its strength from the semantic layout and scene attributes integrated as conditioning variables. We show that our architecture is able to generate realistic outdoor scene images under different conditions, e.g. day-night, sunny-foggy, with clear object boundaries.