AI-Assisted Frame Completion For Traditional Animation
DOI:
https://doi.org/10.29284/ghx8ce31Keywords:
computational power, and GPUs. Such approaches are often impractical for small-scale projects or academic environments.Abstract
Traditional 2D animation requires artists to manually draw a large number of intermediate frames to achieve smooth motion, which is time- consuming and labour-intensive. This paper presents an AI-assisted point-based animation in- Betweening system designed to reduce manual effort by automatically generating intermediate frames from a limited number of keyframes. The proposed system represents animation poses using coordinate points rather than pixel-level images, enabling lightweight computation and structured motion interpolation. The system includes modules for pose data preparation, keyframe input, motion analysis, frame generation, and visualization. Motion between frames is estimated using coordinate interpolation and simple machine learning regression models. Experimental analysis shows that the system produces smooth transitions while maintaining low computational cost. This approach is suitable for beginner animators, educational use, and rapid animation prototyping.
References
1. Zhou et al., “SILK: Smooth Interpolation Framework,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – Human Motion Generation, 2025.
2. Lin et al., “SimMotionEdit: Text-Based Motion Editing,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
3. Kwon et al., “Framer: Interactive Frame Interpolation,” International Conference on Learning Representations (ICLR), 2025.
4. Huang et al., “AceVFI: Video Frame Interpolation: A Comprehensive Survey,” arXiv preprint arXiv, 2025.
5. Zhang et al., “Motion Keyframe Interpolation via Point Cloud Representation,” arXiv preprint arXiv, 2024.
6. Liu et al., “Long-Term Motion In-Betweening via Keyframe Prediction,” Pacific Conference on Computer Graphics and Applications (Pacific Graphics), 2024.
7. Sun et al., “Advanced Articulated Motion Prediction,” Frontiers in Computer Science – Artificial Intelligence Section, Elsevier, 2024.
8. Holden et al., “Motion In-Betweening with Phase Manifolds,” Proceedings of the ACM on Computer Graphics and Interactive Techniques (PACM CGIT), ACM, 2023.
9. Mao et al., “Shuffled Autoregression for Motion Interpolation,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023.
10. Martinez et al., “Sequence-to-Sequence Learning for Human Motion Prediction,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2023.
11. Harvey et al., “Conditional Motion In- Betweening,” Pattern Recognition, Elsevier, 2022.
12. Kim et al., “Global–Local Motion Transformer,” European Conference on Computer Vision (ECCV), Springer, 2022.
13. Chen et al., “Hierarchically Self-Supervised Transformer for Skeleton-Based Representation Learning,” European Conference on Computer Vision (ECCV), Springer, 2022.
14. Sridhar et al., “Transformer-Based Motion In-Betweening,” International Conference of the Italian Association for Artificial Intelligence, Springer, 2022.
15. Wang et al., “Skeleton-Based Motion Prediction: A Survey,” IEEE Access / IEEE Survey-based publication, 2022.
16. Huang et al., “RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation,” European Conference on Computer Vision (ECCV), Springer, 2022.
17. Li et al., “Learning Multiscale Correlations for Human Motion Prediction,” IEEE International Conference on Development and Learning (ICDL), IEEE, 2021.
18. Park et al., “Controllable Human-Centric Keyframe Interpolation,” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, 2021.
19. Tulyakov et al., “TimeLens: Event-Based Video Frame Interpolation,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2021.
20. Cao et al., “Attention-Based Time Series Imputation for Missing Data,” IEEE International Conference on Data Mining (ICDM), IEEE, 2021.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
