跳到主要导航 跳到搜索 跳到主要内容

Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors

  • Guotao Liang
  • , Juncheng Hu
  • , Ximing Xing
  • , Jing Zhang
  • , Qian Yu*
  • *此作品的通讯作者
  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025
出版商Association for Computing Machinery, Inc
9237-9246
页数10
ISBN(电子版)9798400720352
DOI
出版状态已出版 - 27 10月 2025
活动33rd ACM International Conference on Multimedia, MM 2025 - Dublin, 爱尔兰
期限: 27 10月 202531 10月 2025

出版系列

姓名MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025

会议

会议33rd ACM International Conference on Multimedia, MM 2025
国家/地区爱尔兰
Dublin
时期27/10/2531/10/25

指纹

探究 'Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors' 的科研主题。它们共同构成独一无二的指纹。

引用此