A depth sculpturing system comprising:
- an eyewear device including:
- a frame including a bridge;
- a temple connected to a lateral side of the frame;
- and
- a depth-capturing camera, where in the depth-capturing camera includes:
- (i) at least two visible light cameras with overlapping fields of view;
- or (ii) a least one visible light camera and a depth sensor;
- an image display for presenting an initial image, wherein the initial image is a raw image or a processed raw image that is two-dimensional;
- an image display driver coupled to the image display to control the image display to present the initial image;
- a user input device to receive a two-dimensional input selection from a user;
- a memory;
- a processor coupled to the depth-capturing camera, the image display driver, the user input device, and the memory;
- and
- programming in the memory, wherein execution of the programming by the processor configures the depth sculpturing system to perform functions, including functions to:
- generate, via the depth-capturing camera, an initial depth image corresponding to the initial image, wherein:
- the initial depth image is formed of a matrix of vertices, each vertex representing a pixel in a three-dimensional scene;
- each vertex has a position attribute;
- and
- the position attribute of each vertex is based on a three-dimensional location coordinate system and includes an X location coordinate on an X axis for horizontal position, a Y location coordinate on a Y axis for vertical position, and a Z location coordinate on a Z axis for depth;
- present, via the image display, the initial image;
- receive, via the user input device, the two-dimensional input selection of the presented initial image from the user;
- track, via the user input device, motion of the two-dimensional input selection from an initial touch point to a final touch point of the presented initial image;
- compute an initial ray that is a projection from an origin vertex of the three-dimensional location coordinate system to an initial vertex corresponding to the initial touch point of the presented initial image, wherein the origin vertex corresponds to the depth-capturing camera;
- compute a final ray that is the projection from the origin vertex to a final vertex corresponding to the final touch point of the presented initial image;
- determine a rotation matrix between the initial ray and the final ray that describes rotation from the initial ray to the final ray to derive a depth sculpturing region;
- generate a depth sculptured image by applying the rotation matrix to the position attribute of the vertices of the initial depth image in the depth sculpturing region;
- and
- present, via the image display, the depth sculptured image.