Mask Propagation for Efficient Video Semantic Segmentation

Understand

Video Semantic Segmentation (VSS) involves assigning a semantic label to each pixel in a video sequence.

• Prior work in this field has demonstrated promising results by extending image semantic segmentation models to exploit temporal relationships across video frames; however, these approaches often incur significant computational costs.
• In this paper, we propose an efficient mask propagation framework for VSS, called MPVSS.
• Our approach first employs a strong query-based image segmentor on sparse key frames to generate accurate binary masks and class predictions.