Augmented reality images based on color and depth information

摘要

Techniques are described for generating a composite image that depicts a first object with a second object. Two-dimensional images of the first object are captured, along with depth information that includes three-dimensional coordinates of points on the surface of the first object. Based on the depth information, a polygonal model may be determined for the first object including color information determined from the images. The polygonal model of the first object may be placed with a polygonal model of the second object in a virtual scene, and ray tracing operations may generate a plurality of pixels for the composite image. In cases where the first object represents a user and the second object represents a product, the composite image may provide a substantially realistic preview of the user with the product.