Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

AttentionPainter: an efficient and adaptive stroke predictor for scene painting

Tang, Yizhe, Wang, Yue, Hu, Teng, Yi, Ran, Tan, Xin, Ma, Lizhuang, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 2025. AttentionPainter: an efficient and adaptive stroke predictor for scene painting. IEEE Transactions on Visualization and Computer Graphics 10.1109/TVCG.2025.3618184

[thumbnail of TVCG_AttnPainter.pdf]
Preview
PDF - Accepted Post-Print Version
Download (19MB) | Preview

Abstract

Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image. Recently, Neural Painting methods that utilize deep learning and reinforcement learning models to predict the stroke sequences have been developed, but suffer from longer inference time or unstable training. To address these issues, we propose AttentionPainter, an efficient and adaptive model for single-step neural painting. First, we propose a novel scalable stroke predictor, which predicts a large number of stroke parameters within a single forward process, instead of the iterative prediction of previous Reinforcement Learning or auto-regressive methods, which makes AttentionPainter faster than previous neural painting methods. To further increase the training efficiency, we propose a Fast Stroke Stacking algorithm, which brings 13 times acceleration for training. Moreover, we propose Stroke-density Loss, which encourages the model to use small strokes for detailed information, to help improve the reconstruction quality. Finally, we design a Stroke Diffusion Model as an application of AttentionPainter, which conducts the denoising process in the stroke parameter space and facilitates stroke-based inpainting and editing applications helpful for human artists' design. Extensive experiments show that AttentionPainter outperforms the state-of-the-art neural painting methods.

Item Type: Article
Date Type: Published Online
Status: In Press
Schools: Schools > Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers
ISSN: 1077-2626
Date of First Compliant Deposit: 6 October 2025
Date of Acceptance: 29 September 2025
Last Modified: 07 Oct 2025 11:30
URI: https://orca.cardiff.ac.uk/id/eprint/181506

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics