3D Model Generation from 2D Images

Abstract

The application relates to 3D Model Generation from 2D Images. Techniques and systems are described to generate a three-dimensional model from two-dimensional images. A plurality of inputs is received, formed through user interaction with a user interface. Each of the plurality of inputs define a respective user-specified point on the object in a respective one of the plurality of images. A plurality of estimated points on the object are generated automatically and without user intervention. Each of the plurality of estimated points corresponds to a respective user-specified point for other ones of the plurality of images. The plurality of estimated points is displayed for the other ones of the plurality of images in the user interface by a computing device. A mesh of the three-dimensional model of the object is generated by the computing device by mapping respective ones of the user-specified points to respective ones of the estimated points in the plurality of images.

Description

technical field [0001] This application relates to 3D model generation from 2D images. Background technique [0002] In the digital media environment, 3D models can be used to support a variety of functions. Examples of this functionality include use in games, support for modeling different views of an object in successive images to generate a video, use by a 3D printer to print a physical representation of the model, etc. [0003] However, conventional techniques for generating three-dimensional models often require specialized knowledge on the part of the user to interact with complex user interfaces. Accordingly, these conventional techniques are often overwhelming for users, time consuming, and may also require a large amount of space to support a user interface, thereby limiting these techniques to use with feature-rich computing devices. In a general example, a user interacts with a user interface to generate simple shapes, such as cubes, spheres, and so on. The use...

AI Technical Summary

Problems solved by technology

Therefore, in this example, requires the user to already have an example of the object being modeled, requires expensive machinery, or otherwise produces a low quality model with noise and errors

As such, conventional 3D model generation techniques are unintuitive, expensive and require extensive knowledge, and are therefore limited to use in a limited number of instances

Images