用神经隐式+视频扩散模型，自动把矢量图变流畅动画。
LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors
- 用隐式神经表示重建矢量图，保持无限分辨率和精确形状。
- 借助预训练视频扩散模型的运动先验优化动画轨迹。
- 生成动画更自然流畅，适合需要高质量矢量动画的用户。
矢量图形因其可缩放性和易用性，提供了与传统像素图像不同的视觉内容表达方式。通过元素运动驱动的矢量图形动画具有更强的可理解性和可控性，但通常需要大量手动操作。为实现自动化，我们提出一种新方法，将隐式神经表示与文本到视频扩散模型结合用于矢量图形动画。该方法采用分层隐式神经表示重建矢量图形，保留其固有属性，如无限分辨率、精确颜色与形状约束，有效弥合了矢量图形与扩散模型之间的领域差异。随后，利用视频得分蒸馏采样（video score distillation sampling）优化神经表示，借助预训练文本到视频扩散模型的运动先验。最后，通过形变匹配使矢量图形与表示对齐，生成平滑动画。实验表明，本方法能生成生动自然的矢量图形动画，在灵活性与动画质量上显著优于现有技术。
原文摘要 · Abstract (English)
Vector graphics, known for their scalability and user-friendliness, provide a unique approach to visual content compared to traditional pixel-based images. Animation of these graphics, driven by the motion of their elements, offers enhanced comprehensibility and controllability but often requires substantial manual effort. To automate this process, we propose a novel method that integrates implicit neural representations with text-to-video diffusion models for vector graphic animation. Our approach employs layered implicit neural representations to reconstruct vector graphics, preserving their inherent properties such as infinite resolution and precise color and shape constraints, which effectively bridges the large domain gap between vector graphics and diffusion models. The neural representations are then optimized using video score distillation sampling, which leverages motion priors from pretrained text-to-video diffusion models. Finally, the vector graphics are warped to match the representations resulting in smooth animation. Experimental results validate the effectiveness of our method in generating vivid and natural vector graphic animations, demonstrating significant improvement over existing techniques that suffer from limitations in flexibility and animation quality.
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。