Semantic segmentation is an essential and widely-used approach for image analysis in computer vision. In layman’s term, it is able to decide with high certainty if a pixel in a given frame belongs to human, or the background. Overall, the background blurring technology can be described as a process that - first utilizing a - Convolutional Neural Network (CNN) which learns labeled portrait pixels through deep learning, followed by doing semantic segmentation of portrait and shoulders of people shown in video chat and blurring background. Overview of the Mechanism of Background Blur PingWest recently sat down with researchers and engineers from Microsoft Research Asia (MSRA), the company’s most well-known research department, to learn about how this feature came about. Most of them were in the game far earlier than Teams, but none of them has come up with feature similar to Microsoft's background blur.īackground blur protects people’s privacy and prevents embarrassing and unforeseen situations from happening. With a click of a button, the software is able to automatically identify the main person in the feed and blur out basically all the rest.Ī few other major players are in the team collaboration business, including Google's G Suite, Facebook's Workplace and Slack. Last year Microsoft introduced a background blur feature into its work collaboration software called Microsoft Teams. On other occasions, probably we did not have time to tidy up our bedrooms so all messy stuffs in the rooms are shown to interviewers, making your conference scene looks unprofessional. You won't feel embarrassed any more by using this feature!Įver felt embarrassed when doing a conference call on your computer at home? At least this guy did, when his kids marched in during a live interview with BBC.įor most of the times, we got the kids part under control, but problems still remain. Inside Microsoft Teams' Background Blur: A Technical Explanation Inside Microsoft Teams' Background Blur: A Technical Explanation - PingWest English 中文
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |