Abstraction in Style: Beyond Texture and Color

Min Lu; Yuanfeng He; Anthony Chen; Jianhuang He; Pu Wang; Daniel Cohen-Or; Hui Huang

cs.CVMar 31, 2026

Abstraction in Style: Beyond Texture and Color

Authors: Min Lu, Yuanfeng He, Anthony Chen, Jianhuang He, Pu Wang, Daniel Cohen-Or, Hui Huang

Organizations: Shenzhen University, China · Visual Computing Research Center (VCC), College of Computer Science and Software Engineering (CSSE), Shenzhen University, China · Peking University, China

Abstract

Artistic styles often embed abstraction beyond surface appearance, involving deliberate reinterpretation of structure rather than mere changes in texture or color. Conventional style transfer methods typically preserve the input geometry and therefore struggle to capture this deeper abstraction behavior, especially for illustrative and nonphotorealistic styles. In this work, we introduce Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. Given a target image and a small set of style exemplars, AiS first derives an intermediate abstraction proxy that reinterprets the target's structure in accordance with the abstraction logic exhibited by the style. The proxy captures semantic structure while relaxing geometric fidelity, enabling subsequent stylization to operate on an abstracted representation rather than the original image. In a second stage, the abstraction proxy is rendered to produce the final stylized output, preserving visual coherence with the reference style. Both stages are implemented using a shared image space analogy, enabling transformations to be learned from visual exemplars without explicit geometric supervision. By decoupling abstraction from appearance and treating abstraction as an explicit, transferable process, AiS supports a wider range of stylistic transformations, improves controllability, and enables more expressive stylization.

Figures & tables

Figure 1. Abstraction in Style (AiS): Across four challenging illustrative styles with strong structural abstraction, AiS generates coherent results for target images from a small set of exemplars, extending style transfer beyond color and texture to include geometric and structural deformations. Reference images sourced from Pinterest; © original authors.

Figure 2. Conventional style transfer keeps the structure of the target image. Introducing an abstraction stage prior to the stylization, allows adopting structural attributes from the reference, leading to a more coherent transformation.

Figure 3. Two stages of AiS: in the abstraction stage, the target image is reshaped following the reference, generating an abstraction proxy ; Then, in the second stage, the proxy is stylized to produce the final output.

Figure 4. Structural Abstraction Process: given a target image, its hidden backbone is first computed via skeleton detection and area erosion. An abstraction proxy is then generated by the A-VAT, which is trained to learn the visual analogy from the Backbone $\rightarrow$ Proxy pairs in the reference set, e.g., the pair of roosters.

Figure 5. Hidden Backbone Construction: four examples are shown. For each example, the process proceeds as follows: the input target image (left) is first vectorized into simplified flat-color shapes (middle); the skeleton is then detected, and regions are eroded to yield the final hidden structure (right).

Figure 6. Examples of Abstraction Proxies Inferred by A-VATs: for the same hidden backbone in each row, distinct abstraction proxies are generated by different A-VATs which are trained on different reference respectively.

Figure 7. Visual Analogy Transfer (VAT) realized with DiT and LoRA: A visual transformation is expressed as a $2\times 2$ analogy, where a reference pair ( $A\rightarrow A^{\prime}$ ) defines a relation that is applied to a new input ( $B$ ) by predicting the missing panel ( $B^{\prime}$ ). VAT is implemented using a Diffusion Transformer (DiT) conditioned on the visible panels, with a lightweight LoRA used to adapt the model to the analogy relation.

Figure 8. Mix of Three Different A-VATs with Four S-VATs: giving the same S-VAT, the generated outputs share visual appearance (color, texture) but exhibit distinct geometry, demonstrating independent control of style and structure.

Figure 9. Generated examples in which textual elements are stylized with the primary visual content.

Figure 10. Ablation of the Eroded Region Cues in Hidden Backbone: skeleton-only representation (i.e., without eroded regions) can produce a geometrically degraded abstraction proxy.

Figure 11. Ablation of the Abstraction Stage: the two ablated framework variants, without Abstraction and with only Vector Simplification , fail to generalize visual logic. Their outputs exhibit geometry that strictly adheres to the original input target.

Figure 12. Comparison of the two-stage (A-VAT + S-VAT) and a distilled single-stage variant (AS-VAT). The single-stage AS-VAT fails to synthesize coherent results, yielding visual artifacts such as "holes," color bleeding, and rigid adherence to input geometry.

Metrics	StyleID	A.D.	StyleA.	B-LoRA	ZipLoRA
CSD	0.36	0.54	0.22	0.37	0.34
Style FID	529.05	431.12	511.59	495.20	547.73
CLIP-I	0.62	0.69	0.61	0.63	0.66
	K-LoRA	Nano Ban.	AiS (Ablation Study)
	K-LoRA	Nano Ban.	w/o Abs.	+ Vec. Simpl.	AiS (Full)
CSD	0.25	0.56	0.46	0.66	0.75 $\uparrow$

Table 1. Quantitative comparison of baseline methods and ablations.

Figure 13. Generated examples: For the target image in each row, its style-agnostic hidden backbone is first generated. Then, five stylized outputs are produced, one for each reference style (columns). For each style, the system uses a trained A-VAT to generate an abstraction proxy (left grayscale image in each pair), which is then stylized via the corresponding S-VAT to create the final result (right image in the pair).

Figure 14. Generated examples: Each column corresponds to a different target image. Each row corresponds to a different reference style (with one exemplar shown per style), which is applied to all targets in that row. The full set for each style comprises 5 to 10 exemplars, available in the supplementary material.

Figure 15. Design examples mixing up the reference exemplars and the results generated by AiS: on the side are the original images from which the results are generated. The original images are ordered according to the result positions in the example, from top to bottom, left to right.

Figure 16. Qualitative comparison with baseline methods: existing methods struggle with abstract styles and over-rigidly preserve input structure, producing unsatisfactory results. Our method excels at capturing nuanced artistic styles while maintaining natural structural variations. A larger version of this figure, including additional examples, is provided in the supplementary material.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 17. Reference exemplars and $2\times 2$ image training samples for A-VAT ( Backbone $\rightarrow$ Proxy ) and S-VAT ( Proxy $\rightarrow$ Output).

Figure 18. Ablation of the $2\times 2$ Analogy Layout Design: training S-VAT with $1\times 2$ image composite fails to learn the effective style transferring.

Figure 19. Ablation of the Grayscale Proxy Design: In Color S-VAT (color proxy $\rightarrow$ output), the color from the proxy is effectively transferred to the output. In contrast, S-VAT (grayscale proxy $\rightarrow$ output) infers new colors for the proxy that align with the reference.

Figure 20. Full sets of exemplars in sampled references: for each reference style, it shows the number of exemplars in the set (# Exemplars) and the number of training images for VAT (# Training Images).

Figure 21. Gallery of generated examples (part I).

Figure 22. Gallery of generated examples (part II).

Figure 24. Evaluation tests with baseline methods (part I).

Figure 25. Evaluation tests with baseline methods (part II).

Figure 26. Generated consistent design sets from diverse inputs (part I).

Figure 27. Generated consistent design sets from diverse inputs (part II).

Image Style Transfer

Image style transfer changes an image’s visual appearance to match an artistic, photographic, or other reference while preserving its content.

See all 61 papers

Mixture of Style Experts for Diverse Image Stylization
Mar 17, 2026Shihao Zhu, Ziheng Ouyang, Yijia Kang +5Image Style Transfer Diffusion-Based Image Generation
VCIP, CS, Nankai University · Tianjin University · vivo BlueImage Lab +1
StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References
Mar 11, 2026Boyu He, Yunfan Ye, Chang Liu +3Image Style Transfer Diffusion-Based Image Editing
College of Computer Science and Technology, National University of Defense Technology · School of Design, Hunan University
Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training
Sep 3, 2026Xinglin HuImage Style Transfer Diffusion Models
School of Data Science, The Chinese University of Hong Kong, Shenzhen

Mar 17, 2026J/K move · Enter open · S save

Mixture of Style Experts for Diverse Image Stylization

Shihao Zhu, Ziheng Ouyang, Yijia Kang, Qilong Wang+4

VCIP, CS, Nankai University · Tianjin University · vivo BlueImage Lab+1

Image Style Transfer Diffusion-Based Image Generation Mixture of Experts

Open paper AskPDF arXiv

Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/.

Abstract

Image Style Transfer

Explore similar work

Mixture of Style Experts for Diverse Image Stylization

StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References

Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training