3D MODEL CONSTRUCTION FROM 2D ASSETS

Number: 20180322695
Published: 2018-11-08
Filed: 2017-05-08
Assignee: Disney Enterprises, Inc.
Inventors: CHAPMAN; STEVEN M.; PATEL; MEHUL
CPC: G01C11/08; G06T15/50; G06T17/00; G06T17/10; G06T5/00; G06T7/579
Verdict: Medium Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

3D reconstruction from 2D assets.

Abstract

Features of the surface of an object of interest captured in a two-dimensional (2D) image are identified and marked for use in point matching to align multiple 2D images and generating a point cloud representative of the surface of the object in a photogrammetry process. The features which represent actual surface features of the object may have their local contrast enhanced to facilitate their identification. Reflections on the surface of the object are suppressed by correlating such reflections with, e.g., light sources, not associated with the object of interest so that during photogrammetry, such reflections can be ignored, resulting in the creation of a 3D model that is an accurate representation of the object of interest. Prior to local contrast enhancement and the suppression of reflection information, identification and isolation of the object of interest can be improved through one or more filtering processes.

Background

TECHNICAL FIELD

The present disclosure relates generally to image processing.DESCRIPTION OF THE RELATED ART

Photogrammetry can refer to the science of making measurements from photographs. The output of a photogrammetry process can be used to generate a map, drawing, measurement, a three-dimensional (3D) model of a real-world object or scene, etc. Photogrammetry has its origins in aerial photography, where an aircraft-mounted camera pointed towards the ground would take overlapping (two-dimensional (2D)) photos as the aircraft flew along a flight path. The photos could be processed in a stereo-plotter that would let an operator see two photos at once in stereo view, allowing terrain models or topographic maps to be generated.BRIEF SUMMARY OF THE DISCLOSURE

In accordance with one embodiment, a computer-implemented method comprises performing at least one of local contrast enhancement and spectral suppression in relation to an object captured in each of a plurality of two dimensional (2D) images. Photogrammetry may be performed on the plurality of 2D images based upon information indicative of the local contrast enhancement and spectral suppression. Moreover, a computerized three dimensional (3D) model of the object may be generated based upon output information from the performance of photogrammetry.

The performance of local contrast enhancement comprises identifying and isolating one or more features of a surface of the object and increasing contrast i

Claims

1. A computer-implemented method, comprising: perform at least one of local contrast enhancement and spectral suppression in relation to an object captured in each of a plurality of two dimensional (2D) images; perform photogrammetry on the plurality of 2D images based upon information indicative of the local contrast enhancement and spectral suppression; and generate a computerized three dimensional (3D) model of the object based upon output information from the performance of photogrammetry. 12. A computer-implemented method, comprising: identifying an object in a media content; retrieving one or more two dimensional (2D) images representative of the media content in which the object is present; filtering the one or more 2D images to obtain a subset of the one or more 2D images best representing the object; performing at least one of local contrast enhancement and spectral suppression on a surface of the object; generating optimized versions of the subset of the one or more 2D images based upon the information obtained through the performance of the at least one of local contrast enhancement and spectral suppression; and generating a three dimensional (3D) model of the object based upon the optimized versions of the subset of the one or more 2D images.