逆向还原绘画过程，生成艺术创作时间轴视频。
Inverse Painting: Reconstructing The Painting Process
- 从空白画布开始，逐步生成绘画过程的时序图像。
- 基于真实绘画视频训练，能复现多种艺术风格。
- 结合文本与区域理解，实现可控、逼真的创作模拟。
给定一幅输入画作，本文旨在重建其可能的绘制过程，生成一段时间流逝的创作视频。该任务被建模为自回归图像生成问题：从一张空白画布出发，逐步迭代更新。模型通过学习大量真实艺术家的绘画视频来训练，利用文本和区域理解能力定义一系列绘画“指令”，并通过一种新型扩散渲染器更新画布。该方法不仅能还原训练中使用的丙烯画风格，还能在多种艺术风格和题材上生成合理结果，展现出良好的泛化能力。
原文摘要 · Abstract (English)
Given an input painting, we reconstruct a time-lapse video of how it may have been painted. We formulate this as an autoregressive image generation problem, in which an initially blank "canvas" is iteratively updated. The model learns from real artists by training on many painting videos. Our approach incorporates text and region understanding to define a set of painting "instructions" and updates the canvas with a novel diffusion-based renderer. The method extrapolates beyond the limited, acrylic style paintings on which it has been trained, showing plausible results for a wide range of artistic styles and genres.
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。