# EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer

arXiv: https://arxiv.org/abs/1811.10352 · HTML: https://mlsanity.com/paper/1811.10352/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 13 of 13)

- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [General Image-to-Image Translation with One-Shot Image Guidance](https://mlsanity.com/paper/2307.14352/) (2023)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention](https://mlsanity.com/paper/2210.12381/) (2022)
- [Deformable One-shot Face Stylization via DINO Semantic Guidance](https://mlsanity.com/paper/2403.00459/) (2024)
- [ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization](https://mlsanity.com/paper/2308.12452/) (2023)
- [TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer](https://mlsanity.com/paper/2309.06004/) (2023)
- [Mixture of Style Experts for Diverse Image Stylization](https://mlsanity.com/paper/2603.16649/) (2026)
- [Style Transfer with Target Feature Palette and Attention Coloring](https://mlsanity.com/paper/2111.04028/) (2021)
- [Edge Enhanced Image Style Transfer via Transformers](https://mlsanity.com/paper/2301.00592/) (2023)
- [Painterly Image Harmonization via Adversarial Residual Learning](https://mlsanity.com/paper/2311.08646/) (2023)

## Abstract (arXiv)

Style transfer has been an important topic both in computer vision and graphics. Since the seminal work of Gatys et al. first demonstrates the power of stylization through optimization in the deep feature space, quite a few approaches have achieved real-time arbitrary style transfer with straightforward statistic matching techniques. In this work, our key observation is that only considering features in the input style image for the global deep feature statistic matching or local patch swap may not always ensure a satisfactory style transfer; see e.g., Figure 1. Instead, we propose a novel transfer framework, EFANet, that aims to jointly analyze and better align exchangeable features extracted from content and style image pair. In this way, the style features from the style image seek for the best compatibility with the content information in the content image, leading to more structured stylization results. In addition, a new whitening loss is developed for purifying the computed content features and better fusion with styles in feature space. Qualitative and quantitative experiments demonstrate the advantages of our approach.