Artificially rendering images using viewpoint interpolation and extrapolation
Various embodiments of the present invention relate generally to mechanisms and processes relating to artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes applying a transform to estimate a path outside the trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The process also includes generating an artificially rendered image corresponding to a third location positioned on the path. The artificially rendered image is generated by interpolating a transformation from the first location to the third location and from the third location to the second location, gathering image information from the first frame and the second frame by transferring first image information from the first frame to the third frame and second image information from the second frame to the third frame, and combining the first image information and the second image information.
1. A method comprising:
obtaining a content model from a surround view, wherein the surround view is a multi-view interactive digital media representation and the content model is a foreground three-dimensional model including at least one object, wherein the content model comprises one or more layers;
obtaining a context model from the surround view, wherein the context model is a background panoramic representation including scenery surrounding the at least one object, wherein the context model comprises one or more layers; and
generating an artificially rendered image corresponding to a first viewpoint by projecting the content model into a first frame corresponding to the first viewpoint and projecting the panoramic representation into the first frame, wherein the artificially rendered image is generated by moving different layers in different motions, wherein generating the artificially rendered image includes generating using viewpoint-interpolation and any missing information is filled in using viewpoint-extrapolation, wherein viewpoint-extrapolation is achieved by moving different layers in a motion perpendicular to the trajectory from the first frame to a second frame.
2. The method of claim 1 , wherein obtaining the content model from the surround view includes extracting the content model from the surround view.
3. The method of claim 1 , wherein obtaining the context model from the surround view includes extracting the context model from the surround view.
4. The method of claim 1 , wherein the content model and context model are projected according to the depth and orientation of the content model.
5. The method of claim 1 , wherein the surround view is generated from a plurality of images having location information, wherein the plurality of images include at least a portion of overlapping subject matter.
6. The method of claim 5 , wherein the surround view is generated by interpolating data between the plurality of images.
7. The method of claim 5 , wherein the surround view is generated by extrapolating data from the plurality of images.
8. A system comprising:
a processor; and
memory, the memory storing instructions to execute a method, the method comprising:
obtaining a content model from a surround view, wherein the surround view is a multi-view interactive digital media representation and the content model is a foreground three-dimensional model including at least one object, wherein the content model comprises one or more layers;
obtaining a context model from the surround view, wherein the context model is a background panoramic representation including scenery surrounding the at least one object, wherein the context model comprises one or more layers; and
generating an artificially rendered image corresponding to a first viewpoint by projecting the content model into a first frame corresponding to the first viewpoint and projecting the panoramic representation into the first frame, wherein the artificially rendered image is generated by moving different layers in different motions, wherein generating the artificially rendered image includes generating using viewpoint-interpolation and any missing information is filled in using viewpoint-extrapolation, wherein viewpoint-extrapolation is achieved by moving different layers in a motion perpendicular to the trajectory from the first frame to a second frame.
9. The system of claim 8 , wherein obtaining the content model from the surround view includes extracting the content model from the surround view.
10. The system of claim 8 , wherein obtaining the context model from the surround view includes extracting the context model from the surround view.
11. The system of claim 8 , wherein the content model and context model are projected according to the depth and orientation of the content model.
12. The system of claim 8 , wherein the surround view is generated from a plurality of images having location information, wherein the plurality of images include at least a portion of overlapping subject matter.
13. The system of claim 12 , wherein the surround view is generated by interpolating data between the plurality of images.
14. The system of claim 12 , wherein the surround view is generated by extrapolating data from the plurality of images.
15. A non-transitory computer readable medium storing instructions to execute a method, the method comprising:
obtaining a content model from a surround view, wherein the surround view is a multi-view interactive digital media representation and the content model is a foreground three-dimensional model including at least one object, wherein the content model comprises one or more layers;
obtaining a context model from the surround view, wherein the context model is a background panoramic representation including scenery surrounding the at least one object, wherein the context model comprises one or more layers; and
generating an artificially rendered image corresponding to a first viewpoint by projecting the content model into a first frame corresponding to the first viewpoint and projecting the panoramic representation into the first frame, wherein the artificially rendered image is generated by moving different layers in different motions, wherein generating the artificially rendered image includes generating using viewpoint-interpolation and any missing information is filled in using viewpoint-extrapolation, wherein viewpoint-extrapolation is achieved by moving different layers in a motion perpendicular to the trajectory from the first frame to a second frame.
16. The non-transitory computer readable medium of claim 15 , wherein obtaining the content model from the surround view includes extracting the content model from the surround view.
17. The non-transitory computer readable medium of claim 15 , wherein obtaining the context model from the surround view includes extracting the context model from the surround view.
18. The non-transitory computer readable medium of claim 15 , wherein the content model and context model are projected according to the depth and orientation of the content model.
19. The non-transitory computer readable medium of claim 15 , wherein the surround view is generated from a plurality of images having location information, wherein the plurality of images include at least a portion of overlapping subject matter.
20. The non-transitory computer readable medium of claim 15 , wherein the surround view is generated by interpolating data between a plurality of images.