3-D reconstruction using augmented reality frameworks
System and method are provided for scaling a 3-D representation of a building structure. The method includes obtaining images of the building structure, including non-camera anchors. The method also includes identifying reference poses for images based on the non-camera anchors. The method also includes obtaining world map data including real-world poses for the images. The method also includes selecting candidate poses from the real-world poses based on corresponding reference poses. The method also includes calculating a scaling factor for a 3-D representation of the building structure based on correlating the reference poses with the selected candidate poses. Some implementations use structure from motion techniques or LiDAR, in addition to augmented reality frameworks, for scaling the 3-D representations of the building structure. In some implementations, the world map data includes environmental data, such as illumination data, and the method includes generating or displaying the 3-D representation.
1 . A method for generating a scaling factor for a building structure, the method comprising:
obtaining a plurality of images of the building structure, wherein the plurality of images comprises image features co-visible among at least two images;
deriving reference poses for an imager based on the image features;
obtaining world map data including real-world poses of the imager associated with the plurality of images, wherein the real-world poses are derived from an augmented reality framework and comprise geometric position information;
selecting at least two candidate poses from the real-world poses; and
calculating a scaling factor of corresponding reference poses based on the geometric position information of the at least two candidate poses.
2 . The method of claim 1 , further comprising generating a 3-D representation for the building structure based on the plurality of images and the reference poses.
3 . The method of claim 2 , further comprising applying the scaling factor to the 3-D representation.
4 . The method of claim 3 , further comprising extracting a measurement between two pixels in the 3-D representation according to the scaling factor.
5 . The method of claim 1 , wherein the world map data is obtained while capturing the plurality of images.
6 . The method of claim 5 , wherein the world map data includes tracking states for the imager for an associated real-world pose, and selecting the at least two candidate poses from the real-world poses comprises selecting real-world poses based on a tracking state validation.
7 . The method of claim 6 , wherein the tracking state validation is a high confidence position.
8 . The method of claim 1 , wherein selecting the candidate poses from the real-world poses is based on translation changes between the real-world poses proportional with translation changes of corresponding reference poses.
9 . The method of claim 1 , wherein selecting the candidate poses from the real-world poses is based on three-dimensional vector changes between the real-world poses proportional with three-dimensional vector changes of corresponding reference poses.
10 . The method of claim 1 , wherein selecting the candidate poses from the real-world poses comprises selecting from an inlier set of real-world poses.
11 . One or more non-transitory computer readable storage media storing instructions that, when executed by one or more processors, cause the one or more processors to execute operations for:
obtaining a plurality of images of a building structure, wherein the plurality of images comprises image features co-visible among at least two images;
deriving reference poses for an imager based on the image features;
obtaining world map data including real-world poses of the imager associated with the plurality of images, wherein the real-world poses are derived from an augmented reality framework and comprise geometric position information;
selecting at least two candidate poses from the real-world poses; and
calculating a scaling factor of corresponding reference poses based on the geometric position information of the at least two candidate poses.
12 . The one or more non-transitory computer readable storage media of claim 11 , further comprising instructions for generating a 3-D representation for the building structure based on the plurality of images and the reference poses.
13 . The one or more non-transitory computer readable storage media of claim 12 , further comprising instructions for applying the scaling factor to the 3-D representation.
14 . The one or more non-transitory computer readable storage media of claim 13 , further comprising instructions for extracting a measurement between two pixels in the 3-D representation according to the scaling factor.
15 . The one or more non-transitory computer readable storage media of claim 11 , wherein the world map data is obtained while capturing the plurality of images.
16 . The one or more non-transitory computer readable storage media of claim 15 , wherein the world map data includes tracking states for the imager for an associated real-world pose, and selecting the at least two candidate poses from the real-world poses comprises selecting real-world poses based on a tracking state validation.
17 . The one or more non-transitory computer readable storage media of claim 16 , wherein the tracking state validation is a high confidence position.
18 . The one or more non-transitory computer readable storage media of claim 11 , wherein selecting the candidate poses from the real-world poses is based on translation changes between the real-world poses proportional with translation changes of corresponding reference poses.
19 . The one or more non-transitory computer readable storage media of claim 11 , wherein selecting the candidate poses from the real-world poses is based on three-dimensional vector changes between the real-world poses proportional with three-dimensional vector changes of corresponding reference poses.
20 . The one or more non-transitory computer readable storage media of claim 11 , wherein selecting the candidate poses from the real-world poses comprises selecting from an inlier set of real-world poses.