CE-PeopleSeg: Real-Time People Segmentation With 10% CPU Usage for Video Conference

Ziyu Jiang, Zhenhua He, Xueqin Huang, Zibin Yang, Pearl Tan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 914-922

Abstract

Nowadays, video conference solutions are widely adopted for companies, education, and government. People segmentation is crucial for supporting virtual background, an essential video conference function to protect users' privacy. This paper demonstrated a people segmentation framework called CE-PeopleSeg, which employed an efficient segmentation method, structural pruning, and dynamic frame skipping techniques, leading to a fast inference speed on CPU. Our extensive experiments show that the proposed CE-PeopleSeg can achieve a high prediction mIoU of 87.9% on Supervised People Dataset while reaching a real-time inference speed of 32.40 fps on CPU with very low usage of 10%.

Related Material

[pdf]
[bibtex]
@InProceedings{Jiang_2021_CVPR, author = {Jiang, Ziyu and He, Zhenhua and Huang, Xueqin and Yang, Zibin and Tan, Pearl}, title = {CE-PeopleSeg: Real-Time People Segmentation With 10% CPU Usage for Video Conference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {914-922} }