LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering
This dataset addresses a gap for researchers in optical flow estimation and anime-related tasks like video generation, but it is incremental as it focuses on a specific domain.
The authors tackled the lack of optical flow datasets for cel anime character motion by introducing LinkTo-Anime, a high-quality dataset generated from 3D model rendering, which includes 395 video sequences with 24,230 training frames and annotations like optical flow and occlusion masks.
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.