Abstract: A first video stream comprising a first image of a first participant of a virtual meeting, a second image of a second participant, and a third image of a third participant are received from a first client device connected to a virtual meeting platform. It is determined whether an image combining condition is satisfied. Responsive to determining that the image combining condition is satisfied with respect to the first image and the second image, a first screen tile comprising the first image and the second image is generated. A first size of the first screen tile is defined based on a number of images comprised by the first screen tile. A second screen tile comprising the third image is generated. A virtual meeting user interface comprising the first screen tile and the second screen tile is provided for presentation on a second client device connected to the virtual meeting platform.

Abstract: Methods and systems for real-time video enhancement are provided herein. A current frame of a video stream generated by a client device of a plurality of client devices participating in the video conference is identified during a video conference. An enhanced previous frame corresponding to an enhanced version of a previous frame in the video stream is identified. At least the current frame and the enhanced previous frame are provided as input to a machine-learning model. An output of the machine learning model is obtained. The output of the machine learning model indicates an enhanced current frame corresponding to an enhanced version of the current frame. The current frame is replaced with the enhanced current frame in the video stream.

Abstract: In one example in accordance with the present disclosure, a system is described. The system includes a pose estimator to identify a plurality of anatomical points on a person depicted in an image. A frame former of the system generates a frame for the person by connecting a first set of the plurality of anatomical points to form a skeleton and forming at least a head region and a torso region of the person based on a second set of the plurality of anatomical points. A map generator of the system generates a spatial gradient map projecting outwards from the frame. In the system, the spatial gradient map is based on pixel distance from the frame and an intensity along the gradient map indicates a pixels likelihood of form a part of the person.

Abstract: In one example in accordance with the present disclosure, a system is described. The system includes a pose estimator to identify a plurality of anatomical points on a person depicted in an image. A frame former of the system generates a frame for the person by connecting a first set of the plurality of anatomical points to form a skeleton and forming at least a head region and a torso region of the person based on a second set of the plurality of anatomical points. A map generator of the system generates a spatial gradient map projecting outwards from the frame. In the system, the spatial gradient map is based on pixel distance from the frame and an intensity along the gradient map indicates a pixels likelihood of form a part of the person.