Arbitrary view generation
Techniques for generating a prescribed perspective of a composite object are disclosed. In some embodiments, a specification of a composite object comprising a plurality of objects is specified using object views of the plurality of objects that comprise a fixed depth, and a prescribed perspective of the composite object is at least in part generated by populating the prescribed perspective of the composite object with pixels from existing images of the plurality of objects.
1 . A method, comprising:
receiving a specification of a composite object comprising a plurality of objects that is specified using object views of the plurality of objects that comprise a fixed depth; and
generating a prescribed perspective of the composite object at least in part by populating the prescribed perspective of the composite object with pixels from existing images of the plurality of objects.
2 . The method of claim 1 , wherein object views of the plurality of objects that comprise a fixed depth comprise orthographic views of the plurality of objects.
3 . The method of claim 1 , wherein the existing images have the prescribed perspective.
4 . The method of claim 1 , wherein one or more of the existing images that have different perspectives are normalized to the prescribed perspective.
5 . The method of claim 1 , wherein one or more of the existing images are normalized to the prescribed perspective from orthographic views.
6 . The method of claim 1 , wherein one or more of the existing images comprise at least some missing pixels resulting from normalization or transformation to the prescribed perspective from other perspectives.
7 . The method of claim 1 , wherein generating the prescribed perspective of the composite object further comprises interpolating one or more pixels of the prescribed perspective of the composite object.
8 . The method of claim 1 , wherein the specification is received from an interactive application that facilitates manipulation and placement of the plurality of objects to create the composite object.
9 . The method of claim 1 , wherein the specification is received from a visualization or modeling application.
10 . The method of claim 1 , wherein object views of the plurality of objects that comprise a fixed depth facilitate manipulation and placement of the plurality of objects that comprise the composite object.
11 . The method of claim 1 , wherein object views of the plurality of objects that comprise a fixed depth are substantially free of perspective distortions.
12 . The method of claim 1 , wherein the prescribed perspective of the composite object comprises accurate depth.
13 . The method of claim 1 , wherein the prescribed perspective of the composite object comprises accurate relative depth.
14 . The method of claim 1 , wherein an object of the plurality of objects is independently captured or rendered to generate corresponding existing images.
15 . The method of claim 1 , wherein the existing images comprise photographs, photorealistic renderings, or both.
16 . The method of claim 1 , wherein an existing image of the existing images comprises corresponding camera information.
17 . The method of claim 1 , wherein an existing image of the existing images comprises metadata including relative object and camera location and orientation.
18 . The method of claim 1 , wherein an existing image of the existing images comprises metadata including lighting information.
19 . The method of claim 1 , wherein an existing image of the existing images comprises pixel metadata including relative pixel position coordinates.
20 . The method of claim 1 , wherein an existing image of the existing images comprises pixel metadata including surface normal vectors.
21 . The method of claim 1 , wherein an existing image of the existing images comprises pixel metadata including texture mapping coordinates.
22 . The method of claim 1 , wherein an existing image of the existing images comprises pixel metadata encoded in one or more of the red, green, and blue (RGB) channels of the pixels.
23 . The method of claim 1 , wherein the generated prescribed perspective of the composite object comprises a still image or a frame of a video sequence.
24 . A system, comprising:
a processor configured to:
receive a specification of a composite object comprising a plurality of objects that is specified using object views of the plurality of objects that comprise a fixed depth; and
generate a prescribed perspective of the composite object at least in part by populating the prescribed perspective of the composite object with pixels from existing images of the plurality of objects; and
a memory coupled to the processor and configured to provide the processor with instructions.
25 . The system of claim 24 , wherein object views of the plurality of objects that comprise a fixed depth comprise orthographic views of the plurality of objects.
26 . The system of claim 24 , wherein the existing images have the prescribed perspective.
27 . The system of claim 24 , wherein one or more of the existing images that have different perspectives are normalized to the prescribed perspective.
28 . The system of claim 24 , wherein one or more of the existing images are normalized to the prescribed perspective from orthographic views.
29 . The system of claim 24 , wherein one or more of the existing images comprise at least some missing pixels resulting from normalization or transformation to the prescribed perspective from other perspectives.
30 . The system of claim 24 , wherein to generate the prescribed perspective of the composite object further comprises to interpolate one or more pixels of the prescribed perspective of the composite object.
31 . The system of claim 24 , wherein the specification is received from an interactive application that facilitates manipulation and placement of the plurality of objects to create the composite object.
32 . The system of claim 24 , wherein the specification is received from a visualization or modeling application.
33 . The system of claim 24 , wherein object views of the plurality of objects that comprise a fixed depth facilitate manipulation and placement of the plurality of objects that comprise the composite object.
34 . The system of claim 24 , wherein object views of the plurality of objects that comprise a fixed depth are substantially free of perspective distortions.
35 . The system of claim 24 , wherein the prescribed perspective of the composite object comprises accurate depth.
36 . The system of claim 24 , wherein the prescribed perspective of the composite object comprises accurate relative depth.
37 . The system of claim 24 , wherein an object of the plurality of objects is independently captured or rendered to generate corresponding existing images.
38 . The system of claim 24 , wherein the existing images comprise photographs, photorealistic renderings, or both.
39 . The system of claim 24 , wherein an existing image of the existing images comprises corresponding camera information.
40 . The system of claim 24 , wherein an existing image of the existing images comprises metadata including relative object and camera location and orientation.
41 . The system of claim 24 , wherein an existing image of the existing images comprises metadata including lighting information.
42 . The system of claim 24 , wherein an existing image of the existing images comprises pixel metadata including relative pixel position coordinates.
43 . The system of claim 24 , wherein an existing image of the existing images comprises pixel metadata including surface normal vectors.
44 . The system of claim 24 , wherein an existing image of the existing images comprises pixel metadata including texture mapping coordinates.
45 . The system of claim 24 , wherein an existing image of the existing images comprises pixel metadata encoded in one or more of the red, green, and blue (RGB) channels of the pixels.
46 . The system of claim 24 , wherein the generated prescribed perspective of the composite object comprises a still image or a frame of a video sequence.
47 . A computer program product embodied in a non-transitory computer readable storage medium and comprising computer instructions which when executed cause a computer to:
receive a specification of a composite object comprising a plurality of objects that is specified using object views of the plurality of objects that comprise a fixed depth; and
generate a prescribed perspective of the composite object at least in part by populating the prescribed perspective of the composite object with pixels from existing images of the plurality of objects.
48 . The computer program product of claim 47 , wherein object views of the plurality of objects that comprise a fixed depth comprise orthographic views of the plurality of objects.
49 . The computer program product of claim 47 , wherein the existing images have the prescribed perspective.
50 . The computer program product of claim 47 , wherein one or more of the existing images that have different perspectives are normalized to the prescribed perspective.
51 . The computer program product of claim 47 , wherein one or more of the existing images are normalized to the prescribed perspective from orthographic views.
52 . The computer program product of claim 47 , wherein one or more of the existing images comprise at least some missing pixels resulting from normalization or transformation to the prescribed perspective from other perspectives.
53 . The computer program product of claim 47 , wherein to generate the prescribed perspective of the composite object further comprises to interpolate one or more pixels of the prescribed perspective of the composite object.
54 . The computer program product of claim 47 , wherein the specification is received from an interactive application that facilitates manipulation and placement of the plurality of objects to create the composite object.
55 . The computer program product of claim 47 , wherein the specification is received from a visualization or modeling application.
56 . The computer program product of claim 25 , wherein object views of the plurality of objects that comprise a fixed depth facilitate manipulation and placement of the plurality of objects that comprise the composite object.
57 . The computer program product of claim 25 , wherein object views of the plurality of objects that comprise a fixed depth are substantially free of perspective distortions.
58 . The computer program product of claim 47 , wherein the prescribed perspective of the composite object comprises accurate depth.
59 . The computer program product of claim 47 , wherein the prescribed perspective of the composite object comprises accurate relative depth.
60 . The computer program product of claim 47 , wherein an object of the plurality of objects is independently captured or rendered to generate corresponding existing images.
61 . The computer program product of claim 47 , wherein the existing images comprise photographs, photorealistic renderings, or both.
62 . The computer program product of claim 47 , wherein an existing image of the existing images comprises corresponding camera information.
63 . The computer program product of claim 47 , wherein an existing image of the existing images comprises metadata including relative object and camera location and orientation.
64 . The computer program product of claim 47 , wherein an existing image of the existing images comprises metadata including lighting information.
65 . The computer program product of claim 47 , wherein an existing image of the existing images comprises pixel metadata including relative pixel position coordinates.
66 . The computer program product of claim 47 , wherein an existing image of the existing images comprises pixel metadata including surface normal vectors.
67 . The computer program product of claim 47 , wherein an existing image of the existing images comprises pixel metadata including texture mapping coordinates.
68 . The computer program product of claim 47 , wherein an existing image of the existing images comprises pixel metadata encoded in one or more of the red, green, and blue (RGB) channels of the pixels.
69 . The computer program product of claim 47 , wherein the generated prescribed perspective of the composite object comprises a still image or a frame of a video sequence.