In some implementations, a system may receive a plurality of video streams, wherein each video stream is associated with a user of a client device, and wherein the plurality of video streams are associated with a virtual session involving the plurality of client devices. The system may process the plurality of video streams to produce a plurality of processed video streams in which backgrounds of the plurality of video streams are removed. The system may generate a virtual environment that includes a common virtual background, wherein the virtual environment is to be associated with the plurality of processed video streams. The system may transmit one or more output video streams that include the virtual environment with the common virtual background and one or more processed video streams of the plurality of processed video streams.