Manipulating Attributes of Natural Scenes via Hallucination

TL;DR

This paper introduces a two-stage deep learning framework that enables realistic manipulation of natural scene attributes such as season, weather, and time of day by hallucinating and transferring scene appearances without needing reference images.

Contribution

The proposed method allows high-level attribute manipulation of scenes through hallucination, eliminating the need for multiple models or reference images, and preserves semantic details in the output.

Findings

Effective scene attribute manipulation demonstrated through qualitative results.

Quantitative metrics show improved realism over existing methods.

Single model handles multiple attribute changes simultaneously.

Abstract

In this study, we explore building a two-stage framework for enabling users to directly manipulate high-level attributes of a natural scene. The key to our approach is a deep generative network which can hallucinate images of a scene as if they were taken at a different season (e.g. during winter), weather condition (e.g. in a cloudy day) or time of the day (e.g. at sunset). Once the scene is hallucinated with the given attributes, the corresponding look is then transferred to the input image while preserving the semantic details intact, giving a photo-realistic manipulation result. As the proposed framework hallucinates what the scene will look like, it does not require any reference style image as commonly utilized in most of the appearance or style transfer approaches. Moreover, it allows to simultaneously manipulate a given scene according to a diverse set of transient attributes within a single model, eliminating the need of training multiple networks per each translation task. Our comprehensive set of qualitative and quantitative results demonstrate the effectiveness of our approach against the competing methods.