Understanding Generalized Whitening and Coloring Transform for Universal Style Transfer
Style transfer is a task of rendering images in the styles of other images. In the past few years, neural style transfer has achieved a great success in this task, yet suffers from either the inability to generalize to unseen style images or fast style transfer. Recently, an universal style transfer technique that applies zero-phase component analysis (ZCA) for whitening and coloring image features realizes fast and arbitrary style transfer. However, using ZCA for style transfer is empirical and does not have any theoretical support. In addition, other whitening and coloring transforms (WCT) than ZCA have not been investigated. In this report, we generalize ZCA to the general form of WCT, provide an analytical performance analysis from the angle of neural style transfer, and show why ZCA is a good choice for style transfer among different WCTs and why some WCTs are not well applicable for style transfer.
Code (0)
등록된 구현이 없습니다.
Tasks
Style TransferSimilar Papers 제목 키워드 기반
Universal Style Transfer via Feature Transforms
Universal style transfer aims to transfer arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen…
Image ReconstructionStyle TransferWhitening and Coloring transform for GANs
Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for repr…
Whitening and Coloring batch transform for GANs
Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for repre…
Image GenerationAdaWCT: Adaptive Whitening and Coloring Style Injection
Adaptive instance normalization (AdaIN) has become the standard method for style injection: by re-normalizing features through scale-and-shift operations, it has found widespread use in style transfer, image generation, …
Image GenerationImage-to-Image TranslationStyle TransferTranslationA Closed-form Solution to Universal Style Transfer
Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of VGG network as the encoders and trains s…
FormStyle Transfer