AdaWCT: Adaptive Whitening and Coloring Style Injection
Not on the map. Why?
Abstract (arXiv)
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, and image-to-image translation. In this work, we present a generalization of AdaIN which relies on the whitening and coloring transformation (WCT) which we dub AdaWCT, that we apply for style injection in large GANs. We show, through experiments on the StarGANv2 architecture, that this generalization, albeit conceptually simple, results in significant improvements in the quality of the generated images.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 1 Aug 2022.
Builds on
23 of 31 references.
References · 23
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2022Generative Adversarial Networkscited by 5,627
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
- 2021Alias-Free Generative Adversarial Networkscited by 1,184
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
- 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
- 2016Least Squares Generative Adversarial Networkscited by 1,001
- 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
11 more
- 2020Whitening for Self-Supervised Representation Learningcited by 279
- 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
- 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 213
- 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
- 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
- 2017Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networkscited by 92
- 2018Decorrelated Batch Normalizationcited by 83
- 2019Diversity-Sensitive Conditional Generative Adversarial Networkscited by 77
- 2017Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalizationcited by 65
- 2019A Closed-form Solution to Universal Style Transfercited by 42
- 2018Conditional Image-to-Image Translationcited by 30
Built on by
Not cited yet.