Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.02733 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913963514527744 |
|---|---|
| author | Feng, Xiaoyi Zou, Kaifeng Cen, Caichun Huang, Tao Guo, Hui Huang, Zizhou Zhao, Yingli Zhang, Mingqing Zheng, Ziyuan Wang, Diwei Zou, Yuntao Li, Dagang |
| author_facet | Feng, Xiaoyi Zou, Kaifeng Cen, Caichun Huang, Tao Guo, Hui Huang, Zizhou Zhao, Yingli Zhang, Mingqing Zheng, Ziyuan Wang, Diwei Zou, Yuntao Li, Dagang |
| contents | Existing optical flow datasets focus primarily on real-world simulation or synthetic human motion, but few are tailored to Celluloid(cel) anime character motion: a domain with unique visual and motion characteristics. To bridge this gap and facilitate research in optical flow estimation and downstream tasks such as anime video generation and line drawing colorization, we introduce LinkTo-Anime, the first high-quality dataset specifically designed for cel anime character motion generated with 3D model rendering. LinkTo-Anime provides rich annotations including forward and backward optical flow, occlusion masks, and Mixamo Skeleton. The dataset comprises 395 video sequences, totally 24,230 training frames, 720 validation frames, and 4,320 test frames. Furthermore, a comprehensive benchmark is constructed with various optical flow estimation methods to analyze the shortcomings and limitations across multiple datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02733 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering Feng, Xiaoyi Zou, Kaifeng Cen, Caichun Huang, Tao Guo, Hui Huang, Zizhou Zhao, Yingli Zhang, Mingqing Zheng, Ziyuan Wang, Diwei Zou, Yuntao Li, Dagang Computer Vision and Pattern Recognition Artificial Intelligence Existing optical flow datasets focus primarily on real-world simulation or synthetic human motion, but few are tailored to Celluloid(cel) anime character motion: a domain with unique visual and motion characteristics. To bridge this gap and facilitate research in optical flow estimation and downstream tasks such as anime video generation and line drawing colorization, we introduce LinkTo-Anime, the first high-quality dataset specifically designed for cel anime character motion generated with 3D model rendering. LinkTo-Anime provides rich annotations including forward and backward optical flow, occlusion masks, and Mixamo Skeleton. The dataset comprises 395 video sequences, totally 24,230 training frames, 720 validation frames, and 4,320 test frames. Furthermore, a comprehensive benchmark is constructed with various optical flow estimation methods to analyze the shortcomings and limitations across multiple datasets. |
| title | LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.02733 |