Method for editing computer-generated images to maintain alignment between objects specified in frame space and objects specified in scene space
In an image processing system, artist specifications for an inserted object that are specified in frame space are aligned with object points in a virtual scene space. For other frames, where the object points move in the frame space, the object movements are applied to the inserted object in the frame space.
1. A computer-implemented method for processing image data, the method comprising:
under the control of one or more computer systems configured with executable instructions:
obtain generated imagery comprising a plurality of frames representing objects of a geometric model positioned in a virtual scene space and their movement, if any, wherein the generated imagery is from a perspective of a camera position in the virtual scene space;
obtain an artist selection of an input frame from among the plurality of frames;
obtain an image insertion for inclusion onto, or relative to, the input frame;
determine an attachment object set, wherein the attachment object set comprises one or more objects of the geometric model that the image insertion is to track;
determine a set of point associations, wherein a first point association of the set of point associations is a first data structure representing (1) reference coordinates of a first point on a first object of the attachment object set, wherein a reference coordinate is a coordinate independent of at least one position change, in the virtual scene space, of the first object, (2) a second point on the image insertion, and (3) a position, in the input frame, of the second point relative to the first point,
determine a second frame from among the plurality of frames distinct from the input frame; and
determine a correspondence vector, for the point association, as between the input frame and the second frame, the correspondence vector representing changes in position in frame space of the first point from the input frame to the second frame.
2. The computer-implemented method of claim 1 , further comprising using the correspondence vector to define a region in the second frame, wherein the correspondence vector maps position changes in the input frame relative to the second frame or position changes in the second frame relative to the input frame.
3. The computer-implemented method of claim 1 , wherein the image insertion is a texture to be applied to the first object of the attachment object set.
4. The computer-implemented method of claim 1 , wherein the attachment object set is determined based on artist input of object selection.
5. The computer-implemented method of claim 1 , wherein the correspondence vector is determined as part of a motion vector determination over a plurality of motions in the virtual scene space.
6. The computer-implemented method of claim 1 , wherein the correspondence vector represents motion of the camera position and motion of objects in the virtual scene space.
7. The computer-implemented method of claim 1 , wherein the position, in the input frame, of the second point relative to the first point is a same position.
8. The computer-implemented method of claim 1 , wherein the second frame is later in time in the plurality of frames relative to the input frame.
9. The computer-implemented method of claim 1 , wherein the second frame is earlier in time in the plurality of frames relative to the input frame.
10. The computer-implemented method of claim 1 , wherein the second frame is immediately preceding or succeeding in time relative to the input frame.
11. The computer-implemented method of claim 1 , wherein the second frame is in a different time sequence but uses a shared set of reference coordinates with the input frame.
12. The computer-implemented method of claim 1 , wherein the set of point associations consists of a single point association.
13. The computer-implemented method of claim 1 , wherein the image insertion is represented by a texture map.
14. A non-transitory computer-readable storage medium storing instructions, which when executed by at least one processor of a computer system, causes the computer system to carry out the method of claim 1 .
15. A non-transitory computer-readable medium carrying instructions, which when executed by at least one processor of a computer system, causes the computer system to carry out the method of claim 1 .
16. A computer system for generating image data, the computer system comprising:
at least one processor; and
a non-transitory computer-readable medium storing instructions, which when executed by the at least one processor, causes the computer system to:
obtain generated imagery comprising a plurality of frames representing objects of a geometric model positioned in a virtual scene space and their movement, if any, wherein the generated imagery is from a perspective of a camera position in the virtual scene space;
obtain an artist selection of an input frame from among the plurality of frames;
obtain an image insertion for inclusion onto, or relative to, the input frame;
determine an attachment object set, wherein the attachment object set comprises one or more objects of the geometric model that the image insertion is to track;
determine a set of point associations, wherein a first point association of the set of point associations is a first data structure representing (1) reference coordinates of a first point on a first object of the attachment object set, wherein a reference coordinate is a coordinate independent of at least one position change, in the virtual scene space, of the first object, (2) a second point on the image insertion, and (3) a position, in the input frame, of the second point relative to the first point,
determine a second frame from among the plurality of frames distinct from the input frame; and
determine a correspondence vector, for the point association, as between the input frame and the second frame, the correspondence vector representing changes in position in frame space of the first point from the input frame to the second frame.