English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Manipulating Attributes of Natural Scenes via Hallucination

MPS-Authors
/persons/resource/persons127761

Akata,  Zeynep
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1808.07413.pdf
(Preprint), 9MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Karacan, L., Akata, Z., Erdem, A., & Erdem, E. (2018). Manipulating Attributes of Natural Scenes via Hallucination. Retrieved from http://arxiv.org/abs/1808.07413.


Cite as: http://hdl.handle.net/21.11116/0000-0002-1823-C
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.