ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

Abstract

Universal style transfer retains styles from reference images in content images. While existing methods have achieved state-of-the-art style transfer performance, they are not aware of the content leak phenomenon that the image content may corrupt after several rounds of stylization process. In this paper, we propose ArtFlow to prevent content leak during universal style transfer. ArtFlow consists of reversible neural flows and an unbiased feature transfer module. It supports both forward and backward inferences and operates in a projection-transfer-reversion scheme. The forward inference projects input images into deep features, while the backward inference remaps deep features back to input images in a lossless and unbiased way. Extensive experiments demonstrate that ArtFlow achieves comparable performance to state-of-the-art style transfer methods while avoiding content leak.

CVPR 2021 Accepted

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• NICE: Non-linear Independent Components Estimation
• A Learned Representation For Artistic Style
• Fast Patch-based Style Transfer of Arbitrary Style
• Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• CREST: Convolutional Residual Learning for Visual Tracking
• Stylizing Face Images via Multiple Exemplars
• Learning to Hallucinate Face Images via Component Generation and Enhancement
• Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
• Geometric Style Transfer