Saved in:
Bibliographic Details
Main Authors: Liu, Jinfan, Zhang, Wuze, Hu, Zhangli, Zhao, Zhehan, Chen, Ye, Ni, Bingbing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.02752
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911564496371712
author Liu, Jinfan
Zhang, Wuze
Hu, Zhangli
Zhao, Zhehan
Chen, Ye
Ni, Bingbing
author_facet Liu, Jinfan
Zhang, Wuze
Hu, Zhangli
Zhao, Zhehan
Chen, Ye
Ni, Bingbing
contents In stroke-based rendering, search methods often get trapped in local minima due to discrete stroke placement, while differentiable optimizers lack structural awareness and produce unstructured layouts. To bridge this gap, we propose a dual representation that couples discrete polylines with continuous Bézier control points via a bidirectional mapping mechanism. This enables collaborative optimization: local gradients refine global stroke structures, while content-aware stroke proposals help escape poor local optima. Our representation further supports Gaussian-splatting-inspired initialization, enabling highly parallel stroke optimization across the image. Experiments show that our approach reduces the number of strokes by 30-50%, achieves more structurally coherent layouts, and improves reconstruction quality, while cutting optimization time by 30-40% compared to existing differentiable vectorization methods.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02752
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation
Liu, Jinfan
Zhang, Wuze
Hu, Zhangli
Zhao, Zhehan
Chen, Ye
Ni, Bingbing
Computer Vision and Pattern Recognition
In stroke-based rendering, search methods often get trapped in local minima due to discrete stroke placement, while differentiable optimizers lack structural awareness and produce unstructured layouts. To bridge this gap, we propose a dual representation that couples discrete polylines with continuous Bézier control points via a bidirectional mapping mechanism. This enables collaborative optimization: local gradients refine global stroke structures, while content-aware stroke proposals help escape poor local optima. Our representation further supports Gaussian-splatting-inspired initialization, enabling highly parallel stroke optimization across the image. Experiments show that our approach reduces the number of strokes by 30-50%, achieves more structurally coherent layouts, and improves reconstruction quality, while cutting optimization time by 30-40% compared to existing differentiable vectorization methods.
title Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.02752