Please use this identifier to cite or link to this item:
Title: Perceptual-aware sketch simplification based on integrated VGG layers
Author(s): Liu, Xueting 
Author(s): Xu, X.
Xie, M.
Miao, P.
Qu, W.
Xiao, W.
Zhang, H.
Wong, T.-T.
Issue Date: 2021
Publisher: IEEE
Journal: IEEE Transactions on Visualization and Computer Graphics 
Volume: 27
Issue: 1
Start page: 178
End page: 189
Deep learning has been recently demonstrated as an effective tool for raster-based sketch simplification. Nevertheless, it remains challenging to simplify extremely rough sketches. We found that a simplification network trained with a simple loss, such as pixel loss or discriminator loss, may fail to retain the semantically meaningful details when simplifying a very sketchy and complicated drawing. In this paper, we show that, with a well-designed multi-layer perceptual loss, we are able to obtain aesthetic and neat simplification results preserving semantically important global structures as well as fine details without blurriness and excessive emphasis on local structures. To do so, we design a multi-layer discriminator by fusing all VGG feature layers to differentiate sketches and clean lines. The weights used in layer fusing are automatically learned via an intelligent adjustment mechanism. Furthermore, to evaluate our method, we compare our method to state-of-the-art methods through multiple experiments, including visual comparison and intensive user study.
DOI: 10.1109/TVCG.2019.2930512
CIHE Affiliated Publication: Yes
Appears in Collections:CIS Publication

SFX Query Show full item record

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.