Papers › Flow-based Video Segmentation for Human Head and Shoulders

Flow-based Video Segmentation for Human Head and Shoulders

20 Apr 2021arXiv:2104.09752archive 2025-07-28

Zijian Kuang, Xinran Tie

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: \url{https://github.com/kuangzijian/Flow-Based-Video-Matting}.

PaperPDFCode

Code

kuangzijian/Flow-Based-Video-Matting mentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderImage MattingImage SegmentationOptical Flow EstimationSegmentationSemantic SegmentationVideo MattingVideo SegmentationVideo Semantic Segmentation

Datasets

Introduced by this paper, per the archive.

ConferenceVideoSegmentationDataset

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections