Publication Type

Journal Article

Version

acceptedVersion

Publication Date

1-2026

Abstract

This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesthetic outcomes. Inspired by the human painting process, i.e., observing, comparing, and drawing, we incorporate differential image analysis into a neural oil painting model, allowing the model to effectively concentrate on the incremental impact of successive brushstrokes. To operationalize this concept, we propose the Differential Query Transformer (DQ-Transformer), a new architecture that leverages differentially derived image representations enriched with positional encoding to guide the stroke prediction process. This integration enables the model to maintain heightened sensitivity to local details, resulting in more refined and nuanced stroke generation. Furthermore, we incorporate adversarial training into our framework, enhancing the accuracy of stroke prediction and thereby improving the overall realism and fidelity of the synthesized paintings. Extensive qualitative evaluations, complemented by a controlled user study, validate that our DQ-Transformer surpasses existing methods in both visual realism and artistic authenticity, typically achieving these results with fewer strokes.

Keywords

Automatic Oil Painting, Stroke-based Rendering, Style Transfer, Sequence Prediction

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

IEEE Transactions on Visualization and Computer Graphics

Volume

32

Issue

7

First Page

5415

Last Page

5426

ISSN

1077-2626

Identifier

10.1109/TVCG.2026.3669142

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TVCG.2026.3669142

Download

Share

COinS