Three-dimensional modeling toolkit

1. A system comprising:

a memory; and

at least one hardware processor coupled to the memory and comprising instructions that causes the system to perform operations comprising:

accessing a first data stream at a client device, the first data stream comprising image data that comprises a set of image bits that comprise attributes, the image data depicting an object;

accessing a bit mask that corresponds with the object depicted by the image data from among a plurality of bit masks, the bit mask identifying a portion of the set of image bits of the image data based on the attributes of the portion of the set of image bits;

accessing a second data stream at the client device, the second data stream comprising depth data associated with the portion of the image data identified by the bit mask;

generating a point cloud based on the depth data, the point cloud comprising a set of data points that define surface features of an object depicted in the first data stream; and

causing display of a visualization of the point cloud at the client device.

2. The system of claim 1 , wherein the instructions cause the system to perform operations further comprising:

receiving an input that selects a subset of the set of data points of the point cloud;

applying a label to the subset of the set of data points;

generating a training dataset based on the label and the subset of the set of data points; and

fitting a machine learned model to the training dataset.

3. The system of claim 1 , wherein the instructions cause the system to perform operations further comprising:

accessing the point cloud;

identifying a plurality of landmarks based on the point cloud;

determining a classification associated with the point cloud based on the plurality of landmarks;

retrieving a 3D model based on the classification and the plurality of landmarks; and

applying the 3D model to a position in a 3D space relative to the point cloud, based on the plurality of landmarks of the point cloud.

4. The system of claim 3 , wherein the instructions cause the system to perform operations further comprising:

generating a value based on the position of the 3D model relative to the point cloud; and

causing display of the value at the client device.

5. The system of claim 1 , wherein the image data comprises a set of attributes, and the instructions cause the system to perform operations further comprising:

selecting the bit mask from among the plurality of bit masks based on at least the set of attributes of the image data.

6. The system of claim 1 , wherein the applying the bit mask to the first data stream includes:

receiving an input that selects the bit mask from among a plurality of bit masks.

7. The system of claim 1 , wherein the causing display of the visualization of the point cloud includes:

presenting the visualization of the point cloud upon a presentation of the first data stream at the client device.

8. A method comprising:

accessing a first data stream at a client device, the first data stream comprising image data that comprises a set of image bits that comprise attributes, the image data depicting an object;

accessing a bit mask that corresponds with the object depicted by the image data from among a plurality of bit masks, the bit mask identifying a portion of the set of image bits of the image data based on the attributes of the portion of the set of image bits;

accessing a second data stream at the client device, the second data stream comprising depth data associated with the portion of the image data identified by the bit mask;

generating a point cloud based on the depth data, the point cloud comprising a set of data points that define surface features of an object depicted in the first data stream; and

causing display of a visualization of the point cloud at the client device.

9. The method of claim 8 , wherein the method further comprises:

receiving an input that selects a subset of the set of data points of the point cloud;

applying a label to the subset of the set of data points;

generating a training dataset based on the label and the subset of the set of data points; and

fitting a machine learned model to the training dataset.

10. The method of claim 8 , wherein the method further comprises:

accessing the point cloud;

identifying a plurality of landmarks based on the point cloud;

determining a classification associated with the point cloud based on the plurality of landmarks;

retrieving a 3D model based on the classification and the plurality of landmarks; and

applying the 3D model to a position in a 3D space relative to the point cloud, based on the plurality of landmarks of the point cloud.

11. The method of claim 10 , wherein the method further comprises:

generating a value based on the position of the 3D model relative to the point cloud; and

causing display of the value at the client device.

12. The method of claim 8 , wherein the image data comprises a set of attributes, and the method further comprises:

selecting the bit mask from among the plurality of bit masks based on at least the set of attributes of the image data.

13. The method of claim 8 , wherein the applying the bit mask to the first data stream includes:

receiving an input that selects the bit mask from among a plurality of bit masks.

14. The method of claim 8 , wherein the causing display of the visualization of the point cloud includes:

presenting the visualization of the point cloud upon a presentation of the first data stream at the client device.

15. Anon-transitory machine-readable storage medium, storing instructions which, when executed by at least one processor of a machine, cause the machine to perform operations comprising:

accessing a first data stream at a client device, the first data stream comprising image data that comprises a set of image bits that comprise attributes, the image data depicting an object;

accessing a bit mask that corresponds with the object depicted by the image data from among a plurality of bit masks, the bit mask identifying a portion of the set of image bits of the image data based on the attributes of the portion of the set of image bits;

accessing a second data stream at the client device, the second data stream comprising depth data associated with the portion of the image data identified by the bit mask;

generating a point cloud based on the depth data, the point cloud comprising a set of data points that define surface features of an object depicted in the first data stream, and

causing display of a visualization of the point cloud at the client device.

16. The non-transitory machine-readable storage medium of claim 15 , wherein the instructions cause the machine to perform operations further comprising:

receiving an input that selects a subset of the set of data points of the point cloud;

applying a label to the subset of the set of data points;

generating a training dataset based on the label and the subset of the set of data points; and

fitting a machine learned model to the training dataset.

17. The non-transitory machine-readable storage medium of claim 15 , wherein the instructions cause the machine to perform operations further comprising:

accessing the point cloud;

identifying a plurality of landmarks based on the point cloud;

determining a classification associated with the point cloud based on the plurality of landmarks;

retrieving a 3D model based on the classification and the plurality of landmarks; and

applying the 3D model to a position in a 3D space relative to the point cloud, based on the plurality of landmarks of the point cloud.

18. The non-transitory machine-readable storage medium of claim 17 , wherein the instructions cause the machine to perform operations further comprising:

generating a value based on the position of the 3D model relative to the point cloud; and

causing display of the value at the client device.

19. The non-transitory machine-readable storage medium of claim 15 , wherein the image data comprises a set of attributes, and the instructions cause the machine to perform operations further comprising:

selecting the bit mask from among the plurality of bit masks based on at least the set of attributes of the image data.

20. The non-transitory machine-readable storage medium of claim 15 , wherein the applying the bit mask to the first data stream includes:

receiving an input that selects the bit mask from among a plurality of bit masks.