Depth-aware neural style transfer

Liu, Xiao-Chang, Cheng, Ming-Ming, Lai, Yu-Kun and Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 2017. Depth-aware neural style transfer. Presented at: NPAR Non-Photorealistic Animation and Rendering, Los Angeles, CA, USA, 29-30 July 2017. Published in: Spencer, S. N. ed. NPAR '17 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering. Association for Computing Machinery, p. 4. 10.1145/3092919.3092924

Preview

PDF - Accepted Post-Print Version Download (23MB) | Preview

Abstract

Neural style transfer has recently received significant attention and demonstrated amazing results. An efficient solution proposed by Johnson et al. trains feed-forward convolutional neural networks by defining 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 often focus on the primary target and neglect other details. As a result, when input images contain multiple objects potentially at different depths, the resulting images are often unsatisfactory because image layout is destroyed and the boundary between the foreground and background as well as different objects becomes obscured. We observe that the depth map effectively reflects the spatial distribution in an image and preserving the depth map of the content image after 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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Association for Computing Machinery
ISBN:	9781450350815
Date of First Compliant Deposit:	3 August 2017
Date of Acceptance:	8 May 2017
Last Modified:	02 Nov 2022 11:50
URI:	https://orca.cardiff.ac.uk/id/eprint/103272

Citation Data

Cited 40 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item