Smoothing 3D models of objects to mitigate artifacts

1. A non-transitory computing-device readable storage medium on which computing-device readable instructions of a program are stored, the instructions, when executed by one or more computing devices, causing the one or more computing devices to perform a method, the method comprising:

receiving a plurality of polygons representing a three-dimensional model of a surface of a geographic object, the three-dimensional model being based on a comparison of a first image and a second image capturing the surface of the object, where each image is captured from a different camera location;

determining a first pixel location of the first image;

determining a second pixel location of the second image based on visual similarity to the first pixel location;

determining a first ray extending from the first pixel location and a second ray extending from the second pixel location, wherein each ray is associated with a camera angle of a pixel location;

determining a first intersection location associated with the first pixel location at which the first ray intersects a surface represented by the three-dimensional model;

determining a second intersection location associated with the second pixel location at which the second ray intersects a surface represented by the three-dimensional model;

determining a confidence value based on the distance between the first and second intersection locations; and

smoothing a portion of the three-dimensional model by decreasing distances between vertices of a plurality of the polygons of the portion based on the confidence value.

2. The medium of claim 1 , wherein the polygons of the portion are textured based on the visual characteristics of the first image.

3. The medium of claim 1 , wherein the polygons of the portion are textured based on a projection of the visual characteristics of the first image onto the smoothed portion.

4. The medium of claim 3 , wherein a plurality of pixels of the first image are associated with data representing a camera angle relative to the pixel, and the projection of the visual characteristics is based on the camera angles.

5. The medium of claim 4 , wherein the camera angle data is based on information provided by a geographic component configured to determine a geographic location and orientation of a client device comprising the camera.

6. The medium of claim 5 , wherein the information provided by the geographic component comprises a cardinal direction provided by a compass and an orientation data provided by a gyroscope.

7. The medium of claim 1 , wherein determining the confidence value comprises assigning a relatively higher confidence value when the first and second intersection locations are in a single polygon.

8. The medium of claim 1 , wherein determining the confidence value comprises assigning a relatively lower confidence value when the first and second intersection locations are in two different polygons.

9. A method comprising:

receiving a plurality of polygons representing a three-dimensional model of a surface of a geographic object, the three-dimensional model being based on a comparison of a first image and a second image capturing the surface of the object, where each image is captured from a different camera location;

determining a first pixel location of the first image;

determining a second pixel location of the second image based on visual similarity to the first pixel location;

determining a first ray extending from the first pixel location and a second ray extending from the second pixel location, wherein each ray is associated with a camera angle of a pixel location;

determining a first intersection location associated with the first pixel location at which the first ray intersects a surface represented by the three-dimensional model;

determining a second intersection location associated with the second pixel location at which the second ray intersects a surface represented by the three-dimensional model;

determining a confidence value based on the distance between the first and second intersection locations; and

smoothing a portion of the three-dimensional model by decreasing distances between vertices of a plurality of the polygons of the portion based on the confidence value.

10. The method of claim 9 , wherein the polygons of the portion are textured based on the visual characteristics of the first image.

11. The method of claim 9 , wherein the polygons of the portion are textured based on a projection of the visual characteristics of the first image onto the smoothed portion.

12. The method of claim 11 , wherein a plurality of pixels of the first image are associated with data representing a camera angle relative to the pixel, and the projection of the visual characteristics is based on the camera angles.

13. The method of claim 12 , wherein the camera angle data is based on information provided by a geographic component configured to determine a geographic location and orientation of a client device comprising the camera.

14. The method of claim 13 , wherein the information provided by the geographic component comprises a cardinal direction provided by a compass and an orientation data provided by a gyroscope.

15. The method of claim 9 , wherein determining the confidence value comprises assigning a relatively higher confidence value when the first and second intersection locations are in a single polygon.

16. The method of claim 9 , wherein determining the confidence value comprises assigning a relatively lower confidence value when the first and second intersection locations are in two different polygons.

17. A system comprising:

one or more computing devices, and

memory storing instructions executable by the processor and a model associated with locations on the surface of a geographic feature,

wherein the instructions comprise:

receiving a plurality of polygons representing a three-dimensional model of a surface of a geographic object, the three-dimensional model being based on a comparison of a first image and a second image capturing the surface of the object, where each image is captured from a different camera location;

determining a first pixel location of the first image;

determining a second pixel location of the second image based on visual similarity to the first pixel location;

determining a first ray extending from the first pixel location and a second ray extending from the second pixel location, wherein each ray is associated with a camera angle of a pixel location;

determining a first intersection location associated with the first pixel location at which the first ray intersects a surface represented by the three-dimensional model;

determining a second intersection location associated with the second pixel location at which the second ray intersects a surface represented by the three-dimensional model;

determining a confidence value based on the distance between the first and second intersection locations; and

smoothing a portion of the three-dimensional model by decreasing distances between vertices of a plurality of the polygons of the portion based on the confidence value.

18. The system of claim 17 , wherein the polygons of the portion are textured based on the visual characteristics of the first image.

19. The system of claim 17 , wherein the polygons of the portion are textured based on a projection of the visual characteristics of the first image onto the smoothed portion.

20. The system of claim 17 , wherein a plurality of pixels of the first image are associated with data representing a camera angle relative to the pixel, and the projection of the visual characteristics is based on the camera angles.