IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Regular Section
Real-Time Video Matting Based on RVM and Mobile ViT
Chengyu WUJiangshan QINXiangyang LIAo ZHANZhengqiang WANG
Author information
JOURNAL FREE ACCESS

2024 Volume E107.D Issue 6 Pages 792-796

Details
Abstract

Real-time matting is a challenging research in deep learning. Conventional CNN (Convolutional Neural Networks) approaches are easy to misjudge the foreground and background semantic and have blurry matting edges, which result from CNN's limited concentration on global context due to receptive field. We propose a real-time matting approach called RMViT (Real-time matting with Vision Transformer) with Transformer structure, attention and content-aware guidance to solve issues above. The semantic accuracy improves a lot due to the establishment of global context and long-range pixel information. The experiments show our approach exceeds a 30% reduction in error metrics compared with existing real-time matting approaches.

Content from these authors
© 2024 The Institute of Electronics, Information and Communication Engineers
Previous article
feedback
Top