# MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer

arXiv: https://arxiv.org/abs/1812.05233 · HTML: https://mlsanity.com/paper/1812.05233/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2018.

## Built on by (most cited first, 16 of 16)

- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes](https://mlsanity.com/paper/2103.17185/) (2021)
- [ACRE: Abstract Causal REasoning Beyond Covariation](https://mlsanity.com/paper/2103.14232/) (2021)
- [Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning](https://mlsanity.com/paper/2111.12990/) (2021)
- [FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models](https://mlsanity.com/paper/2401.15636/) (2024)
- [MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer](https://mlsanity.com/paper/2211.15313/) (2022)
- [Texture Reformer: Towards Fast and Universal Interactive Texture Transfer](https://mlsanity.com/paper/2112.02788/) (2021)
- [Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer](https://mlsanity.com/paper/2304.11818/) (2023)
- [Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation](https://mlsanity.com/paper/2103.04285/) (2021)
- [AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation](https://mlsanity.com/paper/2305.19245/) (2023)
- [Heterogeneous Adversarial Play in Interactive Environments](https://mlsanity.com/paper/2510.18407/) (2025)
- [Lightweight texture transfer based on texture feature preset](https://mlsanity.com/paper/2306.16846/) (2023)
- [Color and Texture Dual Pipeline Lightweight Style Transfer](https://mlsanity.com/paper/2310.01321/) (2023)
- [Region-controlled Style Transfer](https://mlsanity.com/paper/2310.15658/) (2023)
- [Dual Pipeline Style Transfer with Input Distribution Differentiation](https://mlsanity.com/paper/2311.05432/) (2023)

## Abstract (arXiv)

An unprecedented booming has been witnessed in the research area of artistic style transfer ever since Gatys et al. introduced the neural method. One of the remaining challenges is to balance a trade-off among three critical aspects---speed, flexibility, and quality: (i) the vanilla optimization-based algorithm produces impressive results for arbitrary styles, but is unsatisfyingly slow due to its iterative nature, (ii) the fast approximation methods based on feed-forward neural networks generate satisfactory artistic effects but bound to only a limited number of styles, and (iii) feature-matching methods like AdaIN achieve arbitrary style transfer in a real-time manner but at a cost of the compromised quality. We find it considerably difficult to balance the trade-off well merely using a single feed-forward step and ask, instead, whether there exists an algorithm that could adapt quickly to any style, while the adapted model maintains high efficiency and good image quality. Motivated by this idea, we propose a novel method, coined MetaStyle, which formulates the neural style transfer as a bilevel optimization problem and combines learning with only a few post-processing update steps to adapt to a fast approximation model with satisfying artistic effects, comparable to the optimization-based methods for an arbitrary style. The qualitative and quantitative analysis in the experiments demonstrates that the proposed approach achieves high-quality arbitrary artistic style transfer effectively, with a good trade-off among speed, flexibility, and quality.