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

TL;DR

This paper introduces a dual representation for stroke-based rendering that combines discrete and continuous elements, enabling efficient, high-fidelity painting creation with fewer strokes and faster optimization.

Contribution

It proposes a novel coupled discrete-continuous stroke representation with bidirectional mapping, improving structural coherence and optimization efficiency in differentiable painting methods.

Findings

Reduces stroke count by 30-50%

Improves structural coherence of layouts

Cuts optimization time by 30-40%

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.