DeepAI AI Chat
Log In Sign Up

Flow-based Video Segmentation for Human Head and Shoulders

by   Zijian Kuang, et al.

Video segmentation for the human head and shoulders is essential in creating elegant media for videoconferencing and virtual reality applications. The main challenge is to process high-quality background subtraction in a real-time manner and address the segmentation issues under motion blurs, e.g., shaking the head or waving hands during conference video. To overcome the motion blur problem in video segmentation, we propose a novel flow-based encoder-decoder network (FUNet) that combines both traditional Horn-Schunck optical-flow estimation technique and convolutional neural networks to perform robust real-time video segmentation. We also introduce a video and image segmentation dataset: ConferenceVideoSegmentationDataset. Code and pre-trained models are available on our GitHub repository: <>.


page 1

page 3

page 4

page 5


FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flow

Semi-supervised video object segmentation (VOS) aims to segment a few mo...

Temporally stable video segmentation without video annotations

Temporally consistent dense video annotations are scarce and hard to col...

A Framework for Real-Time Face and Facial Feature Tracking using Optical Flow Pre-estimation and Template Tracking

This work presents a framework for tracking head movements and capturing...

High-quality Panorama Stitching based on Asymmetric Bidirectional Optical Flow

In this paper, we propose a panorama stitching algorithm based on asymme...

JIT-Masker: Efficient Online Distillation for Background Matting

We design a real-time portrait matting pipeline for everyday use, partic...

MEEV: Body Mesh Estimation On Egocentric Video

This technical report introduces our solution, MEEV, proposed to the Ego...