VMFormer: End-to-End Video Matting with Transformer. (arXiv:2208.12801v1 [cs.CV])

Video matting aims to predict the alpha mattes for each frame from a given
input video sequence. Recent solutions to video matting have been dominated by
deep convolutional neural networks (CNN) for the past few years, which have
become the de-facto standard for both academia and industry. However, they have
inbuilt inductive bias of locality and do not capture global characteristics of
an image due to the CNN-based architectures. They also lack long-range temporal
modeling considering computational costs when dealing …

arxiv cv transformer video