Manipulating Attributes of Natural Scenes via Hallucination

Autor: Erkut Erdem, Levent Karacan, Aykut Erdem, Zeynep Akata
Přispěvatelé: Mühendislik ve Doğa Bilimleri Fakültesi -- Bilgisayar Mühendisliği Bölümü, Karacan, Levent
Rok vydání: 2019
Předmět:
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Computer Science - Computer Vision and Pattern Recognition
Multiple networks
02 engineering and technology
Translation (geometry)
Style transfer
Task (project management)
Image (mathematics)
Image generations
Computer graphics
0202 electrical engineering
electronic engineering
information engineering
Natural (music)
Computer vision
Transient (computer programming)
Set (psychology)
Models | Computer vision | Deep generative
business.industry
Image generation
Generative models
Software Engineering
020207 software engineering
Computer Graphics and Computer-Aided Design
Semantics
Photo-realistic
Visual attributes
Quantitative result
Hallucinating
Computer Science
Key (cryptography)
020201 artificial intelligence & image processing
Artificial intelligence
business
Generative model
Natural scenes
Zdroj: ACM Transactions on Graphics. 39:1-17
ISSN: 1557-7368
0730-0301
DOI: 10.1145/3368312
Popis: 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.
Accepted for publication in ACM Transactions on Graphics
Databáze: OpenAIRE
Externí odkaz: