Deep Feature Rotation for Multimodal Image Style Transfer
This addresses the limitation of most style transfer methods that produce only one output per pair, offering a solution for applications requiring varied artistic interpretations.
The paper tackles the problem of generating diverse stylized images from a single content-style pair by proposing Deep Feature Rotation (DFR), a simple method that achieves effective stylization comparable to more complex approaches while producing multiple outputs.
Recently, style transfer is a research area that attracts a lot of attention, which transfers the style of an image onto a content target. Extensive research on style transfer has aimed at speeding up processing or generating high-quality stylized images. Most approaches only produce an output from a content and style image pair, while a few others use complex architectures and can only produce a certain number of outputs. In this paper, we propose a simple method for representing style features in many ways called Deep Feature Rotation (DFR), while not only producing diverse outputs but also still achieving effective stylization compared to more complex methods. Our approach is representative of the many ways of augmentation for intermediate feature embedding without consuming too much computational expense. We also analyze our method by visualizing output in different rotation weights. Our code is available at https://github.com/sonnguyen129/deep-feature-rotation.