论文标题
Animerun：开源3D电影的2D动画视觉通信
AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
论文作者
论文摘要
现有的二维（2D）卡通的通信数据集遭受简单的框架组成和单调运动，因此不足以模拟真实的动画。在这项工作中，我们通过将开源三维（3D）电影转换为2D样式的完整场景，包括新的2D动画视觉通信数据集Animerun，包括同时移动背景和多个主题的交互。我们的分析表明，所提出的数据集不仅在图像组成中更类似于真实的动漫，而且与现有数据集相比，还具有更丰富，更复杂的运动模式。借助此数据集，我们通过评估几种现有的光流和段匹配方法来建立全面的基准，并在动画数据上分析这些方法的缺点。数据，代码和其他补充材料可从https://lisiyao21.github.io/projects/animerun获得。
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.
