MODEL-BASED TEETH RECONSTRUCTION

Number: 20180085201
Published: 2018-03-29
Filed: 2016-09-29
Assignee: Disney Enterprises, Inc.; ETH Zürich (Eidgenössische Technische Hochschule Zürich)
Inventors: Wu; Chenglei et al.
CPC: G16H70/60; A61C13/0004; G16H70/20; G16H50/50
Verdict: Set aside dental/teeth reconstruction, unrelated to entertainment hardware/software
Source: Google Patents · FreePatentsOnline

Abstract

A system and method for non-invasive reconstruction of an entire object-specific or person-specific teeth row from just a set of photographs of the mouth region of an object (e.g., an animal) or a person (e.g., an actor or a patient) are provided. A teeth statistic model defining individual teeth in a teeth row can be developed. The teeth statistical model can jointly describe shape and pose variations per tooth, and as well as placement of the individual teeth in the teeth row. In some embodiments, the teeth statistic model can be trained using teeth information from 3D scan data of different sample subjects. The 3D scan data can be used to establish a database of teeth of various shapes and poses. Geometry information regarding the individual teeth can be extracted from the 3D scan data. The teeth statistic model can be trained using the geometry information regarding the individual teeth.

Background

BACKGROUND OF THE INVENTION

Digital models have become widely used in many fields, from digital animation to remote medical diagnosis. Over the past decades, both research and industry have made tremendous progress when it comes to the creation of digital faces, mostly focusing on appearance, shape, and deformation of skin. More recently, some work has emerged which also targets other facial features, such as the eyes and facial hair. However, capturing the mouth cavity in general, and teeth in particular, has only received very little attention so far. Teeth contribute substantially to the appearance of a face, and expressions may convey a very different intent if teeth are not explicitly modeled. Furthermore, teeth can be an invaluable cue for rigid head pose estimation and are essential for physical simulation, where they serve as a collision boundary. In addition, in medical dentistry, digital teeth models have long become a central asset, since they allow to virtually plan a patient's dental procedure.

Many efforts to capture teeth have stemmed from the medical dental field. While plaster-cast imprints are widely in the past in dental clinics, more and more intra-oral scanners are making their way into the clinics. While these devices can capture the shape of the teeth at high quality, the capture procedure is very invasive and the devices themselves can be costly and may not be readily available. Moreover, although methods using these devices can yield high-

Claims

1. A method for reconstructing a three-dimensional (3D) model of teeth of an object from one or more images of the object, the method being performed by a computer system and comprising: receiving sample data of teeth rows of different sample subjects; establishing geometry correspondence for teeth in the sample subjects; obtaining a teeth statistical model for individual teeth in a generic teeth row, the statistical model encoding a deviation in shape and pose for each individual tooth in the generic teeth row; training the teeth statistical model for the generic teeth row using the teeth in the sample subject with geometry correspondence; and reconstructing a 3D model of teeth of the object by fitting the parameters of the statistical model to teeth information acquired from the one or more images of the object. 10. A system for reconstructing a three-dimensional (3D) model of teeth of an object from one or more images of the object, wherein the system comprises one or more processors configured to execute machine-readable instructions such that when the machine-readable instructions are executed by the one or more processors, the one or more processors are caused to perform: receiving sample data of teeth rows of different sample subjects; establishing geometry correspondence for teeth in the sample subjects; obtaining a teeth statistical model for individual teeth in a generic teeth row, the statistical model encoding a deviation in shape and pose for each individual tooth in the generic teeth row; training the teeth statistical model for the generic teeth row using the teeth in the sample subject with geometry correspondence; and reconstructing a 3D model of teeth of the object by fitting the parameters of the statistical model to teeth information acquired from the one or more images of the object.