Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
Authors:
- Xin WangXWXin Wang
- Geoffrey OxholmGOGeoffrey Oxholm
- Da ZhangDZDa Zhang
- Yuan-Fang WangYWYuan-Fang Wang
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 7178-7186
Abstract
Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced online iterative optimization, enabling nearly real-time stylization. When those stylization networks are applied directly to high-resolution images, however, the style of localized regions often appears less similar to the desired artistic style. This is because the transfer process fails to capture small, intricate textures and maintain correct texture scales of the artworks. Here we propose a multimodal convolutional neural network that takes into consideration faithful representations of both color and luminance channels, and performs stylization hierarchically with multiple losses of increasing scales. Compared to state-of-the-art networks, our network can also perform style transfer in nearly real-time by performing much more sophisticated training offline. By properly handling style and texture cues at multiple scales using several modalities, we can transfer not just large-scale, obvious style cues but also subtle, exquisite ones. That is, our scheme can generate results that are visually pleasing and more similar to multiple desired artistic styles with color and texture cues at multiple scales.Keywords
This publication has 12 references indexed in Scilit:
- Image Style Transfer Using Convolutional Neural Networks2016
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images2015
- Understanding deep image representations by inverting them2015
- Learning to generate chairs with convolutional neural networks2015
- Fast texture transferIEEE Computer Graphics and Applications, 2003
- Graphcut textures2003
- Image quilting for texture synthesis and transfer2001
- Image analogies2001
- Fast texture synthesis using tree-structured vector quantization2000
- Texture synthesis by non-parametric sampling1999