Method of converting 2D video to 3D video using 3D object models

摘要

Method for converting 2D video to 3D video using 3D object models. Embodiments of the invention obtain a 3D object model for one or more objects in a 2D video scene, such as a character. Object models may for example be derived from 3D scanner data; planes, polygons, or surfaces may be fit to this data to generate a 3D model. In each frame in which a modeled object appears, the location and orientation of the 3D model may be determined in the frame, and a depth map for the object may be generated from the model. 3D video may be generated using the depth map. Embodiments may use feature tracking to automatically determine object location and orientation. Embodiments may use rigged 3D models with degrees of freedom to model objects with parts that move relative to one another.

主权项

1. A method of converting 2D video to 3D video using 3D object models, comprising:
obtaining a 2D video; defining a 3D space associated with a scene in said 2D video; obtaining a 3D object model of an object viewable in said scene; identifying one or more frames in said scene, each containing an image of at least a portion of said object; defining a position and orientation of said 3D object model in said 3D space that aligns said 3D object model with the image of said at least a portion of said object in a frame of said one or more frames; generating a depth map associated with the frame from said 3D object model positioned and oriented in said 3D space; assigning depth values in said depth map to other elements in said scene; generating a stereoscopic 3D image pair from the frame and from said depth map.