Abstract: Systems, methods, and computer-readable media for generating 3D models are disclosed. A method includes accessing an image depicting a dental arch of a user. The method further includes identifying, from the image, a set of features of the dental arch. The method further includes generating, using a convolutional neural network, a first voxel grid based on the set of features identified from the image, wherein a shape of the first voxel grid is generated based on a camera projection matrix accounting for a depth of the dental arch depicted in the image. The method further includes generating a 3D model including a 3D surface of the dental arch of the user based on a voxel grid from combining at least a portion of the first voxel grid and a portion of a second voxel grid.

Abstract: 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.