Diversified Arbitrary Style Transfer via Deep Feature Perturbation
arXiv:1909.08223
Abstract
Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style). Although there have been some efforts to improve the diversity of style transfer by introducing an alternative diversity loss, they have restricted generalization, limited diversity and poor scalability. In this paper, we tackle these limitations and propose a simple yet effective method for diversified arbitrary style transfer. The key idea of our method is an operation called deep feature perturbation (DFP), which uses an orthogonal random noise matrix to perturb the deep image feature maps while keeping the original style information unchanged. Our DFP operation can be easily integrated into many existing WCT (whitening and coloring transform)-based methods, and empower them to generate diverse results for arbitrary styles. Experimental results demonstrate that this learning-free and universal method can greatly increase the diversity while maintaining the quality of stylization.
arXiv commentAccepted by CVPR2020
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- One weird trick for parallelizing convolutional neural networks
- A Learned Representation For Artistic Style
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Fast Patch-based Style Transfer of Arbitrary Style
- Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
- Learning Linear Transformations for Fast Arbitrary Style Transfer
- Whitening and Coloring batch transform for GANs
- Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration