Abstract: A system encodes videos acquired of a moving object in a scene by multiple fixed cameras. Camera calibration data of each camera are first determined. The camera calibration data of each camera are associated with the corresponding video. A segmentation mask for each frame of each video is determined. The segmentation mask identifies only foreground pixels in the frame associated with the object. A shape encoder then encodes the segmentation masks, a position encoder encodes a position of each pixel, and a color encoder encodes a color of each pixel. The encoded data can be combined into a single bitstream and transferred to a decoder. At the decoder, the bitstream is decoded to an output video having an arbitrary user selected viewpoint. A dynamic 3D point model defines a geometry of the moving object. Splat sizes and surface normals used during the rendering can be explicitly determined by the encoder, or explicitly by the decoder.

Abstract: A method and system generates 3D video images from point samples obtained from primary video data in a 3D coordinate system. Each point sample contains 3D coordinates in a 3D coordinate system, as well as colour and/or intensity information. On subsequently rendering, the point samples are modified continuously according to an updating of the 3D primary video data. The point samples are arranged in a hierarchic data structure in a manner such that each point sample is an end point, or leaf node, in a hierarchical tree, wherein the branch points in the hierarchy tree are average values of the nodes lower in the hierarchy of the tree.

Abstract: A system encodes videos acquired of a moving object in a scene by multiple fixed cameras. Camera calibration data of each camera are first determined. The camera calibration data of each camera are associated with the corresponding video. A segmentation mask for each frame of each video is determined. The segmentation mask identifies only foreground pixels in the frame associated with the object. A shape encoder then encodes the segmentation masks, a position encoder encodes a position of each pixel, and a color encoder encodes a color of each pixel. The encoded data can be combined into a single bitstream and transferred to a decoder. At the decoder, the bitstream is decoded to an output video having an arbitrary user selected viewpoint. A dynamic 3D point model defines a geometry of the moving object. Splat sizes and surface normals used during the rendering can be explicitly determined by the encoder, or explicitly by the decoder.

Abstract: A method provides a virtual reality environment by acquiring multiple videos of an object such as a person at one location with multiple cameras. The videos are reduced to a differential stream of 3D operators and associated operands. These are used to maintain a 3D model of point samples representing the object. The point samples have 3D coordinates and intensity information derived from the videos. The 3D model of the person can then be rendered from any arbitrary point of view at another remote location while acquiring and reducing the video and maintaining the 3D model in real-time.

Abstract: A method and system generates 3D video images from point samples obtained from primary video data in a 3D coordinate system. Each point sample contains 3D coordinates in a 3D coordinate system, as well as colour and/or intensity information. On subsequently rendering, the point samples are modified continuously according to an updating of the 3D primary video data. The point samples are arranged in a hierarchic data structure in a manner such that each point sample is an end point, or leaf node, in a hierarchical tree, wherein the branch points in the hierarchy tree are average values of the nodes lower in the hierarchy of the tree.