Augmented point cloud for a visualization system and method
A visualization system that uses deep learning can store data representing a scene in multiple layers of representation. Each layer can include a different category of data from the other layers. The categories of data can increase in complexity and specificity from a lowermost layer to an uppermost layer. For instance, first, second, and third layers can store information corresponding to edges, corners, and surface finishes present in the scene, respectively. The visualization system can retrieve data representing the scene from multiple layers, and augment a point cloud representation of the scene in response to the retrieved data. The point cloud can be augmented to increase a point density in one or more point cloud regions that lack data or include only sparse data. Downstream, the visualization system can use the augmented point cloud to create improved images of the scene from desired points of view.
1. A device, comprising:
at least one processor; and
memory including instructions that, when executed on the at least one processor, cause the at least one processor to perform operations, the operations comprising:
retrieving, from a server, data representing a scene from multiple layers, each layer including a different category of data from the other layers, the categories of data increasing in complexity and specificity from a lowermost layer to an uppermost layer; and
augmenting a point cloud representation of the scene in response to the retrieved data.
2. The device of claim 1 , wherein the lowermost layer is a first layer, the first layer storing information corresponding to edges present in the scene.
3. The device of claim 2 , wherein a second layer, above the first layer, stores information corresponding to corners present in the scene.
4. The device of claim 3 , wherein a third layer, above the second layer, stores information corresponding to surface finish present in the scene.
5. The device of claim 1 , wherein the operations are configured such that augmenting the point cloud representation of the scene comprises filling in or fixing at least one hole in the point cloud.
6. The device of claim 1 , wherein the operations are configured such that retrieving the data representing the scene comprises:
wirelessly connecting to a server; and
retrieving the data representing the scene from a non-transitory data storage device communicatively coupled to the server.
7. The device of claim 1 , wherein the operations further comprise forming a first image of the scene from the augmented point cloud.
8. The device of claim 7 , further comprising a display;
wherein the operations further comprise displaying the first image of the scene on the display.
9. The device of claim 8 , wherein the operations further comprise forming a second image of the scene from the augmented point cloud, the second image having a different point of view from the first image.
10. The device of claim 9 , wherein the operations further comprise displaying the second image of the scene on the display.
11. The device of claim 8 , wherein the device is a mobile device.
12. The device of claim 1 , further comprising a left display and a right display, wherein the device is a wearable headset; and
wherein the operations further comprise:
simultaneously generating a left image of the scene and a right image of the scene, the left and right images having respective points of view separated by an interpupillary distance;
displaying the left image of the scene on the left display; and
displaying the right image of the scene on the right display.
13. A method, comprising:
wirelessly connecting to a server, the server storing data representing a scene, the server storing the data in multiple layers, each layer including a different category of data from the other layers, the categories of data increasing in complexity and specificity from a lowermost layer to an uppermost layer;
retrieving, from the server, at least a portion of the data representing the scene; and
augmenting a point cloud representation of the scene in response to the retrieved data.
14. The method of claim 13 , further comprising:
forming a first image of the scene from the augmented point cloud; and
displaying the first image of the scene on a display.
15. The method of claim 14 , further comprising:
forming a second image of the scene from the augmented point cloud, the second image having a different point of view from the first image; and
displaying the second image of the scene on the display.
16. The method of claim 13 , further comprising:
simultaneously generating a left image of the scene and a right image of the scene, the left and right images having respective points of view separated by an interpupillary distance;
displaying the left image of the scene on a left display; and
displaying the right image of the scene on a right display.
17. The method of claim 13 , wherein:
the lowermost layer is a first layer, the first layer storing information corresponding to edges present in the scene;
a second layer, above the first layer, stores information corresponding to corners present in the scene; and
a third layer, above the second layer, stores information corresponding to surface finish present in the scene.
18. A non-transitory machine-readable medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
retrieving data representing a scene from multiple layers, each layer including a different category of data from the other layers, the categories of data increasing in complexity and specificity from a lowermost layer to an uppermost layer; and
augmenting a point cloud representation of the scene in response to the retrieved data.
19. The non-transitory machine-readable medium of claim 18 , wherein:
the lowermost layer is a first layer, the first layer storing information corresponding to edges present in the scene;
a second layer, above the first layer, stores information corresponding to corners present in the scene; and
a third layer, above the second layer, stores information corresponding to surface finish present in the scene.