Embodiments of the present invention are directed to a visual-collaborative systems and methods enabling geographically distributed groups to engage in face-to-face, interactive collaborative video conferences. In one aspect, a method for establishing a collaborative interaction between a local participant and one or more remote participants includes capturing images of the local participant in front of a display screen. The includes collecting depth information of the local participant located in front of the display screen and transmitting the images and depth information of the local participant to the one or more remote participants. The method also includes receiving images and depth information of the one or more remote participants and projecting the images of the one or more remote participants on the display screen based on the depth information of the remote participants.