# A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning

arXiv: https://arxiv.org/abs/2303.12710 · HTML: https://mlsanity.com/paper/2303.12710/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 76 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 30 of 50)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Arbitrary Style Transfer with Style-Attentional Networks](https://mlsanity.com/paper/1812.02342/) (2018)
- [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)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [Style Transfer by Relaxed Optimal Transport and Self-Similarity](https://mlsanity.com/paper/1904.12785/) (2019)
- [Visual Attribute Transfer through Deep Image Analogy](https://mlsanity.com/paper/1705.01088/) (2017)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Controlling Perceptual Factors in Neural Style Transfer](https://mlsanity.com/paper/1611.07865/) (2016)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [StyleBank: An Explicit Representation for Neural Image Style Transfer](https://mlsanity.com/paper/1703.09210/) (2017)
- [Arbitrary Video Style Transfer via Multi-Channel Correlation](https://mlsanity.com/paper/2009.08003/) (2020)

## Built on by (most cited first, 10 of 10)

- [ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models](https://mlsanity.com/paper/2305.16225/) (2023)
- [Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer](https://mlsanity.com/paper/2305.05464/) (2023)
- [DiffArtist: Towards Structure and Appearance Controllable Image Stylization](https://mlsanity.com/paper/2407.15842/) (2024)
- [SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer](https://mlsanity.com/paper/2503.15934/) (2025)
- [Evaluation in Neural Style Transfer: A Review](https://mlsanity.com/paper/2401.17109/) (2024)
- [SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer](https://mlsanity.com/paper/2503.04119/) (2025)
- [Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning](https://mlsanity.com/paper/2602.01335/) (2026)
- [MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention](https://mlsanity.com/paper/2501.00816/) (2025)
- [PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillation](https://mlsanity.com/paper/2502.16996/) (2025)
- [Pluggable Style Representation Learning for Multi-Style Transfer](https://mlsanity.com/paper/2503.20368/) (2025)

## Abstract (arXiv)

We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style transfer models, e.g., CNN-based, ViT-based, and flow-based methods. As the key component in image style transfer tasks, a suitable style representation is essential to achieve satisfactory results. Existing approaches based on deep neural network typically use second-order statistics to generate the output. However, these hand-crafted features computed from a single image cannot leverage style information sufficiently, which leads to artifacts such as local distortions and style inconsistency. To address these issues, we propose to learn style representation directly from a large amount of images based on contrastive learning, by taking the relationships between specific styles and the holistic style distribution into account. Specifically, we present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components, i.e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer. We carry out qualitative and quantitative evaluations to show that our approach produces superior results than those obtained via state-of-the-art methods.