ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
This addresses a specific technical bottleneck in style transfer for computer vision applications, but it is incremental as it builds on existing methods to fix a known issue.
The paper tackles the problem of content leak in universal image style transfer, where image content degrades over multiple stylization rounds, and proposes ArtFlow, a method using reversible neural flows and unbiased feature transfer to prevent this issue while achieving comparable performance to state-of-the-art methods.
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.