让多物体手绘动画更流畅，靠分组与运动先验提升一致性
Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors
- 分两阶段：先分组定关键帧生成粗动画，再用分组位移网络精修
- 在多个复杂多物体场景上，动画时序一致性显著优于现有方法
- 适合需要高质量多对象动态手绘的创作者或交互设计应用
我们提出GroupSketch，一种新型向量手绘动画方法，能有效处理多物体交互与复杂运动。现有方法在多物体场景中表现不佳，或仅限单物体，或存在时间不一致和泛化能力差的问题。为此，我们的方法采用两阶段流程：第一阶段通过交互式划分语义组并定义关键帧，利用插值生成粗略动画；第二阶段提出基于分组的位移网络（GDN），通过文本到视频模型提供的运动先验预测分组特异性位移场，并引入上下文条件特征增强（CCFE）模块以提升时间一致性。大量实验表明，该方法在复杂多物体手绘动画生成中显著优于现有方法，提升了质量与一致性，拓展了手绘动画的实际应用场景。
原文摘要 · Abstract (English)
We introduce GroupSketch, a novel method for vector sketch animation that effectively handles multi-object interactions and complex motions. Existing approaches struggle with these scenarios, either being limited to single-object cases or suffering from temporal inconsistency and poor generalization. To address these limitations, our method adopts a two-stage pipeline comprising Motion Initialization and Motion Refinement. In the first stage, the input sketch is interactively divided into semantic groups and key frames are defined, enabling the generation of a coarse animation via interpolation. In the second stage, we propose a Group-based Displacement Network (GDN), which refines the coarse animation by predicting group-specific displacement fields, leveraging priors from a text-to-video model. GDN further incorporates specialized modules, such as Context-conditioned Feature Enhancement (CCFE), to improve temporal consistency. Extensive experiments demonstrate that our approach significantly outperforms existing methods in generating high-quality, temporally consistent animations for complex, multi-object sketches, thus expanding the practical applications of sketch animation.
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。