Our paper with title of "Face Inpainting based on High-Level Facial Attributes" has been accepted for publication at CVIU

Congrats to my group members, Chen Li, Lap-Fai Yu, Kun Zhou, Stephen Lin and Horst Bischof! Our paper with title of "Face Inpainting based on High-Level Facial Attributes" has been accepted for publication at Computer vision and Image Understanding (CVIU) which is a prestigious (Q1) peer reviewed journal in Computer Vision. 

Face Inpainting based on High-Level Facial Attributes

Mahdi Jampour, Chen Li, Lap-Fai Yu, Kun Zhou, Stephen Lin and Horst Bischof

Abstract: We introduce a novel data-driven approach for face inpainting, which makes use of the observable region of an occluded face as well as its inferred high-level facial attributes, namely gender, ethnicity, and expression. Based on the intuition that the realism of a face inpainting result depends significantly on its overall consistency with respect to these high-level attributes, our approach selects a guidance face that matches the targeted attributes and utilizes it together with the observable input face regions to inpaint the missing areas. These two sources of information are balanced using an adaptive optimization, and the inpainting is performed on the intrinsic  image layers instead of the RGB color space to handle the illumination differences between the target face and the guidance face to further enhance the resulting visual quality. Our experiments demonstrate that this approach is effective in inpainting facial components such as the mouth orthe eyes that could be partially or completely occluded in the input face. A perceptual study shows that our approach generates more natural facial appearances by accounting for high-level facial attributes.

Online: https://doi.org/10.1016/j.cviu.2017.05.008

Free access provided by Elsevier until October 7, 2017 here at https://authors.elsevier.com/a/1VZpp3qy-3EzF2

 

Citation:

Mahdi Jampour, Chen Li, Lap-Fai Yu, Kun Zhou, Stephen Lin, Horst Bischof,
Face inpainting based on high-level facial attributes, Computer Vision and Image Understanding,
Volume 161, 2017, Pages 29-41, ISSN 1077-3142, http://dx.doi.org/10.1016/j.cviu.2017.05.008.
 

 

@article{Jampour2017,

title = "Face inpainting based on high-level facial attributes",

author = "Mahdi Jampour and Chen Li and Lap-Fai Yu and Kun Zhou and Stephen Lin and Horst Bischof",

journal = "Computer Vision and Image Understanding",

volume = "161",

number = "",

pages = "29 - 41",

year = "2017",

}

 


Home  |  Contact me  |  About me  | Mahdi Jampour © 2008-2017