# LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering

arXiv: https://arxiv.org/abs/2506.02733 · HTML: https://mlsanity.com/paper/2506.02733/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [Conditional Image-to-Video Generation with Latent Flow Diffusion Models](https://mlsanity.com/paper/2303.13744/) (2023)
- [Quadratic video interpolation](https://mlsanity.com/paper/1911.00627/) (2019)
- [A Tutorial on Principal Component Analysis](https://mlsanity.com/paper/1404.1100/) (2014)
- [MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask](https://mlsanity.com/paper/2003.10955/) (2020)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [MemFlow: Optical Flow Estimation and Prediction with Memory](https://mlsanity.com/paper/2404.04808/) (2024)
- [A Unified Pyramid Recurrent Network for Video Frame Interpolation](https://mlsanity.com/paper/2211.03456/) (2022)
- [Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation](https://mlsanity.com/paper/2408.09787/) (2024)
- [Disentangling Architecture and Training for Optical Flow](https://mlsanity.com/paper/2203.10712/) (2022)
- [LVCD: Reference-based Lineart Video Colorization with Diffusion Models](https://mlsanity.com/paper/2409.12960/) (2024)
- [The Animation Transformer: Visual Correspondence via Segment Matching](https://mlsanity.com/paper/2109.02614/) (2021)
- [PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters](https://mlsanity.com/paper/2303.14587/) (2023)
- [DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling](https://mlsanity.com/paper/2303.14078/) (2023)
- [Learning Inclusion Matching for Animation Paint Bucket Colorization](https://mlsanity.com/paper/2403.18342/) (2024)
- [AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies](https://mlsanity.com/paper/2211.05709/) (2022)
- [Deep Geometrized Cartoon Line Inbetweening](https://mlsanity.com/paper/2309.16643/) (2023)
- [CogCartoon: Towards Practical Story Visualization](https://mlsanity.com/paper/2312.10718/) (2023)
- [SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches](https://mlsanity.com/paper/2209.00185/) (2022)
- [Paint Bucket Colorization Using Anime Character Color Design Sheets](https://mlsanity.com/paper/2410.19424/) (2024)

## Built on by (most cited first, 2 of 2)

- [HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization](https://mlsanity.com/paper/2607.17994/) (2026)
- [Video Generation Models: A Survey of Post-Training and Alignment](https://mlsanity.com/paper/2610.00812/) (2026)

## Abstract (arXiv)

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.