用少量手绘笔触数据训练出可控的油画笔触生成模型
Data-Efficient Brushstroke Generation with Diffusion Models for Oil Painting
- 基于扩散模型，引入随机视觉先验稳定小样本训练
- 仅用470个样本即可生成结构一致且多样的笔触
- 支持笔触排序与叠加，适合创作有层次的油画作品
许多创意多媒体系统依赖于笔触、纹理等视觉基本单元，但这类数据难以大规模获取，且与自然图像差异显著。本文针对小样本手绘笔触（n=470）生成问题，提出StrokeDiff框架，结合平滑正则化（SmR），在训练中注入随机视觉先验，实现稀疏监督下的模型稳定，且不改变推理过程。通过贝塞尔曲线条件模块实现笔触可控性，并构建完整的笔触驱动绘画流程：预测、生成、排序与合成。实验表明，该方法能生成多样且结构连贯的笔触，提升作品纹理丰富度与层次感，经自动指标与人工评估验证有效。
原文摘要 · Abstract (English)
Many creative multimedia systems are built upon visual primitives such as strokes or textures, which are difficult to collect at scale and fundamentally different from natural image data. This data scarcity makes it challenging for modern generative models to learn expressive and controllable primitives, limiting their use in process-aware content creation. In this work, we study the problem of learning human-like brushstroke generation from a small set of hand-drawn samples (n=470) and propose StrokeDiff, a diffusion-based framework with Smooth Regularization (SmR). SmR injects stochastic visual priors during training, providing a simple mechanism to stabilize diffusion models under sparse supervision without altering the inference process. We further show how the learned primitives can be made controllable through a Bézier-based conditioning module and integrated into a complete stroke-based painting pipeline, including prediction, generation, ordering, and compositing. This demonstrates how data-efficient primitive modeling can support expressive and structured multimedia content creation. Experiments indicate that the proposed approach produces diverse and structurally coherent brushstrokes and enables paintings with richer texture and layering, validated by both automatic metrics and human evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。