# Learning Graph Neural Networks for Image Style Transfer

arXiv: https://arxiv.org/abs/2207.11681 · HTML: https://mlsanity.com/paper/2207.11681/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 65 references that are in the map.
- First posted on arXiv 24 Jul 2022.

## Builds on (most cited first, 30 of 53)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [Style Transfer by Relaxed Optimal Transport and Self-Similarity](https://mlsanity.com/paper/1904.12785/) (2019)
- [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017)
- [The Contextual Loss for Image Transformation with Non-Aligned Data](https://mlsanity.com/paper/1803.02077/) (2018)
- [Distilling Knowledge from Graph Convolutional Networks](https://mlsanity.com/paper/2003.10477/) (2020)
- [Visual Attribute Transfer through Deep Image Analogy](https://mlsanity.com/paper/1705.01088/) (2017)
- [ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond](https://mlsanity.com/paper/2202.10108/) (2022)
- [Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration](https://mlsanity.com/paper/1805.03857/) (2018)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](https://mlsanity.com/paper/1601.04589/) (2016)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [Cross-Scale Internal Graph Neural Network for Image Super-Resolution](https://mlsanity.com/paper/2006.16673/) (2020)
- [Fast Patch-based Style Transfer of Arbitrary Style](https://mlsanity.com/paper/1612.04337/) (2016)
- [Shunted Self-Attention via Multi-Scale Token Aggregation](https://mlsanity.com/paper/2111.15193/) (2021)
- [StyleBank: An Explicit Representation for Neural Image Style Transfer](https://mlsanity.com/paper/1703.09210/) (2017)

## Built on by (most cited first, 29 of 29)

- [Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models](https://mlsanity.com/paper/2303.17599/) (2023)
- [Diffusion Model as Representation Learner](https://mlsanity.com/paper/2308.10916/) (2023)
- [Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks](https://mlsanity.com/paper/2212.05946/) (2022)
- [AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks](https://mlsanity.com/paper/2307.09724/) (2023)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Deep Graph Reprogramming](https://mlsanity.com/paper/2304.14593/) (2023)
- [AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising](https://mlsanity.com/paper/2406.06911/) (2024)
- [MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer](https://mlsanity.com/paper/2211.15313/) (2022)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser](https://mlsanity.com/paper/2311.15040/) (2023)
- [A Graph-Based Approach for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2311.17891/) (2023)
- [Segment Anything in Non-Euclidean Domains: Challenges and Opportunities](https://mlsanity.com/paper/2304.11595/) (2023)
- [Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection](https://mlsanity.com/paper/2307.13529/) (2023)
- [Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization](https://mlsanity.com/paper/2305.19903/) (2023)
- [Disentangled Condensation for Large-scale Graphs](https://mlsanity.com/paper/2401.12231/) (2024)
- [Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer](https://mlsanity.com/paper/2304.11818/) (2023)
- [Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks](https://mlsanity.com/paper/2407.01979/) (2024)
- [Partial Network Cloning](https://mlsanity.com/paper/2303.10597/) (2023)
- [Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems](https://mlsanity.com/paper/2311.11796/) (2023)
- [Relation Rectification in Diffusion Model](https://mlsanity.com/paper/2403.20249/) (2024)
- [GraphBridge: Towards Arbitrary Transfer Learning in GNNs](https://mlsanity.com/paper/2502.19252/) (2025)
- [Interpretable Multi-View Clustering](https://mlsanity.com/paper/2405.02644/) (2024)
- [Schema Inference for Interpretable Image Classification](https://mlsanity.com/paper/2303.06635/) (2023)
- [Message-passing selection: Towards interpretable GNNs for graph classification](https://mlsanity.com/paper/2306.02081/) (2023)
- [Pluggable Neural Machine Translation Models via Memory-augmented Adapters](https://mlsanity.com/paper/2307.06029/) (2023)
- [Adaptive Learned Image Compression with Graph Neural Networks](https://mlsanity.com/paper/2603.25316/) (2026)
- [Retinex-guided Channel-grouping based Patch Swap for Arbitrary Style Transfer](https://mlsanity.com/paper/2309.10528/) (2023)
- [Painterly Image Harmonization via Adversarial Residual Learning](https://mlsanity.com/paper/2311.08646/) (2023)
- [Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models](https://mlsanity.com/paper/2408.13661/) (2024)

## Abstract (arXiv)

State-of-the-art parametric and non-parametric style transfer approaches are prone to either distorted local style patterns due to global statistics alignment, or unpleasing artifacts resulting from patch mismatching. In this paper, we study a novel semi-parametric neural style transfer framework that alleviates the deficiency of both parametric and non-parametric stylization. The core idea of our approach is to establish accurate and fine-grained content-style correspondences using graph neural networks (GNNs). To this end, we develop an elaborated GNN model with content and style local patches as the graph vertices. The style transfer procedure is then modeled as the attention-based heterogeneous message passing between the style and content nodes in a learnable manner, leading to adaptive many-to-one style-content correlations at the local patch level. In addition, an elaborated deformable graph convolutional operation is introduced for cross-scale style-content matching. Experimental results demonstrate that the proposed semi-parametric image stylization approach yields encouraging results on the challenging style patterns, preserving both global appearance and exquisite details. Furthermore, by controlling the number of edges at the inference stage, the proposed method also triggers novel functionalities like diversified patch-based stylization with a single model.