Amazon Technologies, Inc.

Microsoft Technology Licensing, LLC

Thomas Lund Dideriksen

Denis Demandolx

Eric Paul Bennett

Douglas Alan Ricard

Brian P Jackson

Kevin Geeyoung Chiu

Gonzalo Alberto Ramos

Timothy Andrew Ong

Dirk Padfield

Steven Charles Glenner

Jonathan McGuire

Gregory James Nyssen

Brent George

Frederic Laurent Pascal Devernay

Jake Schintgen

Ashok Dave

Devices and techniques are generally described for image-guided three dimensional (3D) modeling. In various examples, a first two-dimensional (2D) image representing an object may be received. A first three-dimensional (3D) model corresponding to the first 2D image may be determined from among a plurality of 3D models. A first selection of a first portion of the first 2D image may be received. A second selection of a second portion of the first 3D model corresponding to the portion of the first 2D image may be received. At least one transformation of the first 3D model may be determined based at least in part on differences between a geometric feature of the first portion of the first 2D image and a geometric feature of the second portion of the first 3D model. A modified 3D model may be generated by applying the at least one transformation to the first 3D model.

Image-guided three dimensional modeling

Systems and methods are described for generating models of three-dimensional objects using an identified template from a library of reference objects. An object may be scanned using a 3D scanner or other computing device, which may generate scan data including a 'point cloud' of geometric points corresponding to the surface of the object. The point cloud or other scan data may be used to identify a reference object that corresponds to the scanned object, and a normalized point cloud may be obtained for the reference object. The normalized point cloud may then be deformed to more accurately fit the shape of the scanned object, and a 3D model may be generated based on the deformed point cloud. Multiple templates may be used to generate a normalized point cloud for an object that partially corresponds to more than one reference object, and images, meshes, wireframes, or other representations may be generated.

3D scanning and modeling system

The display of 3D-representations involves navigation and interaction with users engaged with the display. Points of interest (POIs), as applied to areas of interest for a 3D-representation, are anchored to the 3D-representation on the display and are moveable in synchrony with the 3D-representation navigation. POIs are presented in which interactive actions are associated with the POIs. When a user selects one of the interactive actions associated with a POI, the selection can prompt the display of a new 3D-representation of an item related to the 3D-representation to which the POI is anchored, thereby improving access and analysis about information for related items.

Interactive points of interest for 3D-representations

A robotic coordinate measurement machine (CMM) having a contact direction sensitive (CDS) probe is usable to detect internal dimensions for an object of interest. A robot arm may contact a surface with the CDS probe which may then detect a magnitude and direction of the resulting reaction force. The robotic CMM may monitor the magnitude and/or direction of the reaction force while the CDS probe is being slide across a surface to determine dimensions for the surface. Changes in the reaction force sensed by the CDS probe may be used to identify contact with other surfaces of contours in the surface the CDS probe is being slid across. A path of the CDS probe may be altered based on the contact with other surfaces or the contours.

Internal dimension detection using contact direction sensitive probe

Systems and methods are described for providing an image validation module. The image validation mobile enables capture, enhancement, validation, and upload of a digital image to a networked computing service, applying criteria that correspond to image validation criteria used by the networked computing service. The image validation mobile may be executed on a mobile computing device, and may authenticate itself to the networked computing service to indicate that digital images have already been validated. The image validation module may provide feedback before, during, or after image capture to enable the capture of valid images, and may provide feedback before, during, or after image enhancement to allow issues that prevent a digital image from passing validation to be addressed.

Image validation

Embodiments perform an iterative process for enlarging a rectangle having a fixed aspect ratio within a convex polygon to find the largest rectangular area within the convex polygon. The iterative process includes detecting an intersection of one or more corners of the rectangle with the convex polygon and adjusting a position of the rectangle based on the quantity of intersecting corners. The iterative growth process continues until a maximum inscribed size of the rectangle has been determined. Some embodiments process images from bracketed photography and crop areas outside the determined maximum inscribed size when combining the images into a single image.

Determining a maximum inscribed size of a rectangle

Embodiments provide a unified method for combining images such as high dynamic range images, flash-no-flash image pairs, and/or other images. Weight masks are defined for each of the plurality of images by calculating coefficients for each of the weight masks. Calculating the coefficients includes, at least, performing histogram alignment between a reference image and each of the other input images and by applying a mismatch bias to the coefficients as a function of the histogram alignment. After applying the weight masks to the corresponding images, the images are combined to produce a final image.

Growing community of inventors

Seattle, WA, United States of America

Thomas Lund Dideriksen