Video face segmentation method, device and equipment based on time sequence information

The invention discloses a video face segmentation method and device based on time sequence information, equipment and a storage medium. The method comprises the following steps: constructing and training a face segmentation model; wherein the face segmentation model is provided with a TemporalModule module which is used for capturing time sequence information between video frames; and inputting face video data into the face segmentation model, and performing video face segmentation processing based on the time sequence information to obtain a target face segmentation result. According to the invention, jumping between different frames in video segmentation can be avoided, and the stability of video segmentation is improved. 本发明公开了一种基于时序信息的视频人脸分割方法、装置、设备及存储介质，其包括：构建并训练人脸分割模型；其中，所述人脸分割模型设有用于捕获视频帧之间的时序信息的TemporalModule模块；将人脸视频数据输入至所述人脸分割模型中并基于所述时序信息进行视频人脸分割处理，得到目标人脸分割结果。能够实现视频分割中不同帧之间不会产生跳变的效果，提高视频分割的稳定性。