Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors
Guotao Liang, Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu
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-tovideo 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, multiobject sketches, thus expanding the practical applications of sketch animation. Project page: GroupSketch.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector AnimationGuotao Liang, Zhangcheng Wang, Chuang Wang, Juncheng Hu 等ICML 2026 · 被引用 11 次
- Gated Relational Alignment via Confidence-based Distillation for Efficient VLMsYanlong Chen, Amir Habibian, Luca Benini, Yawei LiICML 2026 · 被引用 5 次
- Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement LearningTongxi Wang, Zhuoyang Xia, Xinran Chen, Shan LiuICML 2026
它引用的顶会 Paper19
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- VideoComposer: Compositional Video Synthesis with Motion ControllabilityXiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen 等NeurIPS 2023 · 被引用 579 次
- DreamFusion: Text-to-3D using 2D DiffusionBen Poole, Ajay Jain, Jonathan T. Barron, Ben MildenhallICLR 2023 · 被引用 463 次
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image EncodersKevin Frans, Lisa B. Soros, Olaf WitkowskiNeurIPS 2022 · 被引用 311 次
相关 Paper
- FlipSketch: Flipping Static Drawings to Text-Guided Sketch AnimationsHmrishav Bandyopadhyay, Yi-Zhe SongCVPR 2025
- Multi-Object Sketch Animation by Scene Decomposition and Motion PlanningJingyu Liu, Zijie Xin, Yuhan Fu, Ruixiang Zhao 等ICCV 2025 · 被引用 6 次
- StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence DiffusionJin Zhou, Yi Zhou, Hongliang Yang, Pengfei Xu 等AAAI 2026 · 被引用 2 次
- Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch InbetweeningJiaming Shen, Kun Hu, Wei Bao, Chang Wen Chen 等ACM MM 2024 · 被引用 5 次
- SwiftSketch: A Diffusion Model for Image-to-Vector Sketch GenerationEllie Arar, Yarden Frenkel, Daniel Cohen-Or, Ariel Shamir 等SIGGRAPH 2025 · 被引用 12 次
