AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
This provides a more realistic dataset for researchers in computer vision and animation, but it is incremental as it builds on existing data creation approaches.
The authors tackled the problem of insufficient 2D animation correspondence datasets by creating AnimeRun, a new dataset converted from open-source 3D movies to simulate real animations with complex scenes and motions, and established a benchmark showing that existing methods have shortcomings on this data.
Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations. In this work, we present a new 2D animation visual correspondence dataset, AnimeRun, by converting open source three-dimensional (3D) movies to full scenes in 2D style, including simultaneous moving background and interactions of multiple subjects. Our analyses show that the proposed dataset not only resembles real anime more in image composition, but also possesses richer and more complex motion patterns compared to existing datasets. With this dataset, we establish a comprehensive benchmark by evaluating several existing optical flow and segment matching methods, and analyze shortcomings of these methods on animation data. Data, code and other supplementary materials are available at https://lisiyao21.github.io/projects/AnimeRun.