Three-dimensional modeling toolkit
A 3D scanning toolkit to perform operations that include: accessing a first data stream at a client device, wherein the first data stream comprises at least image data; applying a bit mask to the first data stream, the bit mask identifying a portion of the image data; accessing a second data stream at the client device, the second data stream comprising depth data associated with the portion of the image data; 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 upon a presentation of the first data stream at the client device.
1. A system comprising:
at least one hardware processor; and
at least one memory storing instructions that, when executed by the at least one hardware processor, causes the system to perform operations comprising:
accessing image data depicting an object, wherein accessing the image data includes activating a camera of a mobile device of a user and generating the image data via the camera of the mobile device, and the object is a portion of the user;
identifying a set of features from the image data;
assigning, utilizing a mask, labels to one or more pixels of the image data based on the set of features identified from the image data, wherein assigning labels to the one or more pixels of the image data comprises, for each respective one or more pixels of the image data, providing features identified from the respective one or more pixels as input into a machine-learned model, yielding a label for the respective one or more pixels, and wherein the one or more labels include semantic labels that correspond with the set of features of the image data;
accessing depth data based on the labels assigned to the one or more pixels utilizing the mask, wherein the mask identifies the image data to access for the depth data associated with the one or more pixels; and
generating a three-dimensional (3D) model of the object based on the labels assigned to the one or more pixels of the image data and the depth data, wherein the 3D model comprises unlabeled pixels and labeled pixels.
2. The system of claim 1 , wherein the generating the 3D model based on the one or more labels includes:
generating the 3D model based on the depth data.
3. The system of claim 1 , wherein the 3D model includes a polygon mesh model.
4. The system of claim 1 , wherein the image data comprises a depiction of an object, and wherein the 3D model comprises a representation of surface features of the object depicted by the image data.
5. The system of claim 1 , wherein the mobile device of the user is a smartphone.
6. A method comprising:
accessing image data depicting an object, wherein accessing the image data includes activating a camera of a mobile device of a user and generating the image data via the camera of the mobile device, and the object is a portion of the user;
identifying a set of features from the image data;
assigning, utilizing a mask, labels to one or more pixels of the image data based on the set of features identified from the image data, wherein assigning labels to the one or more pixels of the image data comprises, for each respective one or more pixels of the image data, providing features identified from the respective one or more pixels as input into a machine-learned model, yielding a label for the respective one or more pixels, wherein the one or more labels include semantic labels that correspond with the set of features of the image data;
accessing depth data based on the labels assigned to the one or more pixels utilizing the mask, wherein the mask identifies the image data to access for the depth data associated with the one or more pixels; and
generating a three-dimensional (3D) model of the object based on the labels assigned to the one or more pixels of the image data and the depth data, wherein the 3D model comprises unlabeled pixels and labeled pixels.
7. The method of claim 6 , wherein the generating the 3D model based on the one or more labels includes:
generating the 3D model based on the depth data of a data stream.
8. The method of claim 6 , wherein the 3D model includes a polygon mesh model.
9. The method of claim 6 , wherein the image data comprises a depiction of an object, and wherein the 3D model comprises a representation of surface features of the object depicted by the image data.
10. A non-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 image data depicting an object, wherein accessing the image data includes activating a camera of a mobile device of a user and generating the image data via the camera of the mobile device, and the object is a portion of the user;
identifying a set of features from the image data;
assigning, utilizing a mask, labels to one or more pixels of the image data based on the set of features identified from the image data, wherein assigning labels to the one or more pixels of the image data comprises, for each respective one or more pixels of the image data, providing features identified from the respective one or more pixels as input into a machine-learned model, yielding a label for the respective one or more pixels, and wherein the one or more labels include semantic labels that correspond with the set of features of the image data;
accessing depth data based on the labels assigned to the one or more pixels utilizing the mask, wherein the mask identifies the image data to access for the depth data associated with the one or more pixels; and
generating a three-dimensional (3D) model of the object based on the labels assigned to the one or more pixels of the image data and the depth data, wherein the 3D model comprises unlabeled pixels and labeled pixels.
11. The non-transitory machine-readable storage medium of claim 10 , wherein the generating the 3D model based on the one or more labels includes:
generating the 3D model based on the depth data.
12. The non-transitory machine-readable storage medium of claim 10 , wherein the 3D model includes a polygon mesh model.
13. The non-transitory machine-readable storage medium of claim 10 , wherein the image data comprises a depiction of an object, and wherein the 3D model comprises a representation of surface features of the object depicted by the image data.