Visible to the public Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer

TitleMultimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
Publication TypeConference Paper
Year of Publication2017
AuthorsWang, X., Oxholm, G., Zhang, D., Wang, Y.
Conference Name2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Date PublishedJuly 2017
ISBN Number978-1-5386-0457-1
Keywordsartistic style transfer, Biological neural networks, color representations, Computer architecture, convolution, hierarchical deep convolutional neural network, high-resolution images, Image color analysis, image colour analysis, image representation, Image resolution, image texture, luminance channels, Metrics, multimodal convolutional neural network, multimodal transfer, neural nets, neural style transfer, Optimization, pubcrawl, resilience, Resiliency, Scalability, stylization networks, texture cues, Training

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.

Citation Keywang_multimodal_2017