paper-with-me

홈 › Papers

Understanding Generalized Whitening and Coloring Transform for Universal Style Transfer

2019-10-01 · ICCV 2019 10 · Tai-Yin Chiu

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Universal Style Transfer via Feature Transforms

2017-05-23 · NeurIPS 2017 12 · Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang 외

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 Transfer

Whitening and Coloring transform for GANs

2019-05-01 · ICLR 2019 5 · Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe

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

2018-06-01 · ICLR 2019 5 · Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe

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 Generation

AdaWCT: Adaptive Whitening and Coloring Style Injection

2022-08-01 · Antoine Dufour, Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith 외

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 TransferTranslation

A Closed-form Solution to Universal Style Transfer

2019-06-03 · ICCV 2019 10 · Ming Lu, Hao Zhao, Anbang Yao, Yurong Chen 외

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