BL30K

BL30K is a synthetic dataset rendered using Blender with ShapeNet's data. We break the dataset into six segments, each with approximately 5K videos. The videos are organized in a similar format as DAVIS and YouTubeVOS, so dataloaders for those datasets can be used directly. Each video is 160 frames long, and each frame has a resolution of 768*512. There are 3-5 objects per video, and each object has a random smooth trajectory -- we tried to optimize the trajectories in a greedy fashion to minimize object intersection (not guaranteed), with occlusions still possible (happen a lot in reality). See [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion (MiVOS), CVPR 2022] for details.

BL30K是一个使用Blender和ShapeNet数据渲染的合成数据集。我们将数据集划分为六个部分，每部分约包含5K个视频。视频的格式与DAVIS和YouTubeVOS相似，因此可以直接使用这些数据集的加载器。每个视频包含160帧，每帧的分辨率为768*512。每个视频中包含3-5个物体，每个物体都具有随机的平滑轨迹——我们尝试以贪婪策略优化轨迹以最小化物体间的交集（不能保证），同时仍然可能存在遮挡（在现实中经常发生）。有关详细信息，请参阅[模块化交互式视频物体分割：交互到掩码，传播和差异感知融合（MiVOS），CVPR 2022]。