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

2026-04-03

AI Summary

This work addresses the limitations of existing stroke-based rendering methods, which either suffer from local optima in discrete search or produce disorganized layouts due to structure-agnostic differentiable optimization. To overcome these issues, the authors propose a dual-parameterization representation that couples discrete polylines with continuous Bézier control points, enabling synergistic optimization through a bidirectional mapping mechanism. Local gradient-based refinement guides global structural coherence, while content-aware stroke proposals facilitate escape from suboptimal solutions. Inspired by Gaussian splatting, a novel initialization strategy supports highly parallel stroke optimization. This approach is the first to unify discrete and continuous stroke representations, achieving both structural consistency and significant efficiency gains: it reduces stroke count by 30–50%, improves reconstruction quality, and shortens optimization time by 30–40% compared to current 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 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.

Problem

• stroke-based rendering
• local minima
• structural awareness
• differentiable optimization
• vectorization

Innovation

• differentiable rendering
• stroke-based painting
• dual parameterization
• Bézier curves
• Gaussian splatting