Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation

arXiv cs.CV / 4/6/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses challenges in stroke-based rendering where discrete stroke placement can cause search to get stuck in local minima while existing differentiable optimizers may yield unstructured layouts.
It introduces a dual parameterization that links discrete polylines with continuous Bézier control points through a bidirectional mapping, enabling gradients to improve global stroke structure and learned stroke proposals to help escape bad local optima.
The method incorporates Gaussian-splatting-inspired initialization to support highly parallel optimization across the image.
Experimental results indicate the approach uses 30–50% fewer strokes, produces more structurally coherent stroke layouts, improves reconstruction quality, and reduces optimization time by 30–40% versus prior differentiable vectorization methods.

Abstract

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 B\'ezier 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.