In this paper, we propose a novel patch-based face hallucination framework, which employs a dual model to hallucinate different components associated with one facial image. Our model is based on a statistical learning approach: associative learning. It suffices to learn the dependencies between low-resolution image patches and their high-resolution ones with a new concept hidden parameter space as a bridge to connect those patches with different resolutions. To compensate higher frequency information of images, we present a dual associative learning algorithm for orderly inferring main components and high frequency components of faces. The patches can be finally integrated to form a whole high-resolution image. Experiments demonstrate that our approach does render high quality superresolution faces.
Face hallucination through dual associative learning
01.01.2005
367090 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Face Hallucination through Dual Associative Learning
British Library Conference Proceedings | 2005
|Face Hallucination: Theory and Practice
British Library Online Contents | 2007
|A Comprehensive Survey to Face Hallucination
British Library Online Contents | 2014
|Unified framework of face hallucination across multiple modalities [9445-24]
British Library Conference Proceedings | 2015
Hallucination of facial details from degraded images using 3D face models
British Library Online Contents | 2015
|