AI绘画助手模拟艺术家持续创作，无需目标图就能自动生成连贯笔触。
PaintCopilot: Modeling Painting as Autonomous Artistic Continuation
- 基于视觉变换器和流匹配，从画布状态预测下一步笔触。
- 支持四种交互模式，可补全笔触或局部重绘，生成效果自然流畅。
- 适合艺术创作者与AI协同创作，提升创意表达效率。
我们提出PaintCopilot，一种协同创作的神经绘画助手，将绘画建模为开放式的自回归艺术行为，依据动态画布状态和历史笔触进行推断，无需目标图像。不同于现有方法将绘画视为向预设参考图像的像素重建，PaintCopilot直接从学习到的艺术动态中预测未来笔触，类比大语言模型根据上下文延续文本序列。框架包含三个互补模型：基于ViT的靶点预测器，从部分画布推断艺术家意图；自回归下一笔预测器，通过流匹配生成时间连贯的笔触；基于VAE的区域采样器，按需合成语义定位的笔触序列。系统采用三种可微笔触表示（Hard Round、Brush Tip、2D Gaussian），支持四种交互工作流：优化历史、笔触补全、区域修复和动态笔刷。通过专业艺术家案例研究，证明PaintCopilot能实现艺术家与AI在创作过程中持续交替控制的流畅协同流程。
原文摘要 · Abstract (English)
We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on evolving canvas states and prior brushstroke history, without requiring a target image. Unlike existing neural painting methods that frame painting as pixel reconstruction toward a predefined reference, PaintCopilot predicts future strokes directly from learned artistic dynamics, analogous to how large language models continue text sequences from prior context. The framework proposes three complementary models: a ViT-based Target Predictor that infers artist intent from partial canvas observations, an autoregressive Next Stroke Predictor that generates temporally coherent brushstrokes via flow matching, and a VAE-based Region Sampler that synthesizes semantically localized stroke sequences on demand. Built on three differentiable brush representations (Hard Round, Brush Tip, and 2D Gaussian), the system supports four interactive workflows: Optimize History, Stroke Completion, Region Inpainting, and Dynamic Brush. Through case studies with professional artists, we demonstrate that PaintCopilot enables fluid co-creative painting workflows in which artists and AI continuously alternate control throughout the creative process.
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。