KwaiVGI/SynCamVideo-Dataset

SynCamVideo数据集是一个使用Unreal Engine 5渲染的多摄像头同步视频数据集，包含1000个不同的场景，每个场景由36个摄像头捕捉，共计36000个视频。该数据集以50种不同的动物作为主要主体，并使用来自Poly Haven的20个不同地点作为背景。在每个场景中，从50种动物中随机选择1-2个主体沿预定轨迹移动，背景从20个地点中随机选择，36个摄像头同时记录主体的运动。该数据集可用于训练多摄像头同步视频生成模型，可应用于电影制作和多视角数据生成等下游任务。The SynCamVideo Dataset is a multi-camera synchronized video dataset rendered using the Unreal Engine 5, consisting of 1,000 different scenes, each captured by 36 cameras, resulting in a total of 36,000 videos. The dataset features 50 different animals as the main subject and utilizes 20 different locations from Poly Haven as backgrounds. In each scene, 1-2 subjects are selected from the 50 animals and move along a predefined trajectory, the background is randomly chosen from the 20 locations, and the 36 cameras simultaneously record the subjects movements. The dataset can be used to train multi-camera synchronized video generation models, applicable in areas such as filmmaking and multi-view data generation for downstream tasks.