Depth-aware Neural Style Transfer

Loading...
Thumbnail Image
Date
2017
Journal Title
Journal ISSN
Volume Title
Publisher
Association for Computing Machinery, Inc (ACM)
Abstract
Neural style transfer has recently received signi cant a ention and demonstrated amazing results. An e cient solution proposed by Johnson et al. trains feed-forward convolutional neural networks by de ning and optimizing perceptual loss functions. Such methods are typically based on high-level features extracted from pre-trained neural networks, where the loss functions contain two components: style loss and content loss. However, such pre-trained networks are originally designed for object recognition, and hence the high-level features o en focus on the primary target and neglect other details. As a result, when input images contain multiple objects potentially at di erent depths, the resulting images are o en unsatisfactory because image layout is destroyed and the boundary between the foreground and background as well as di erent objects becomes obscured. We observe that the depth map e ectively re ects the spatial distribution in an image and preserving the depth map of the content image a er stylization helps produce an image that preserves its semantic content. In this paper, we introduce a novel approach for neural style transfer that integrates depth preservation as additional loss, preserving overall image layout while performing style transfer.
Description

        
@inproceedings{
10.1145:3092919.3092924
, booktitle = {
Non-Photorealistic Animation and Rendering
}, editor = {
Holger Winnemoeller and Lyn Bartram
}, title = {{
Depth-aware Neural Style Transfer
}}, author = {
Liu, Xiao-Chang
and
Cheng, Ming-Ming
and
Lai, Yu-Kun
and
Rosin, Paul L.
}, year = {
2017
}, publisher = {
Association for Computing Machinery, Inc (ACM)
}, ISSN = {
-
}, ISBN = {
978-1-4503-5081-5
}, DOI = {
10.1145/3092919.3092924
} }
Citation
Collections