International Business Machines Corporation

Other

Holly Edith Rushmeier

Fausto Bernardini

Gabriel Taubin

Andre Pierre Gueziec

Richard D Lawrence

Ioana Boier-Martin

Ioana Maria Martin

George S Almasi

Jose Gomes

Laurent Balmelli

Claudio T Silva

Henning Biermann

Frank P Giordano

Joshua D Mittleman

José Gomes

Hisham Emad El-Din ElShishiny

Jingyi Jin

Silvio Savarese

A method for hole-filling in 3D models includes identifying vertices adjacent to hole boundaries in a mesh of points on a digital image and constructing a signed distance function based on vertices adjacent to hole boundaries. A Radial Basis Function is fit based on the constructed signed distance function and evaluated on a grid, which include the hole. The points on the hole surface are extracted and meshed to fill the hole.

System and method for hole filling in 3D models

Disclosed is an improved computer system, method, and program product that has one or more input devices for receiving one or more input meshes representing a three dimensional model. The three dimensional model is capable of being represented as a 2-manifold triangular mesh. A conversion process automatically converts the input mesh to a multiresolution quadrilateral-based subdivision surface (MQSS) representation.

System, method, and program product for extracting a multiresolution quadrilateral-based subdivision surface representation from an arbitrary two-manifold polygon mesh

Disclosed are an image editing user interface system and method. The system includes one or more computers with one or more graphical user interfaces, and a receiving process for receiving one or more rendered two dimensional images on the computer graphical user interface. Each two dimensional image represents reflected light from a lit three dimensional object model, and the reflective light at each point of the two dimensional image corresponds to an object point on the three dimensional object model. The system further includes a changing process for changing a portion of the two dimensional image by changing the light intensity at a set of one or more points on the two dimensional image. The change in light intensity at the set of points causes a change in the three dimensional model to correspond to the change in the light intensity.

Method and structure for image-based object editing

A light source calibration target has a surface in view of a camera of an image capture system, The target includes a substrate having a substantially Lambertian surface, a visually distinct polygonal shape having corners formed on said surface so as to be visually distinct from the surface, and a plurality of objects each having an upstanding tip mounted on the surface, A method of using the calibration target operates, for each of the light sources to be calibrated, to capture an image of the target; process the captured image to derive light source calibration data and to store the calibration data.

System and method for light source calibration

A method and apparatus are disclosed for finding a triangle mesh that interpolates a set of points obtained from a scanning system. A ball-pivoting algorithm computes a triangle mesh interpolating a given point cloud. The disclosed ball-pivoting algorithm triangulates a set of points by 'rolling' a ball of radius r on the point cloud. The points are surface samples acquired with multiple range scans of an object. The ball-pivoting algorithm starts with a seed triangle, and pivots the ball of a given radius, r, around an edge of the triangle. During the pivoting operation, the ball revolves around the edge while keeping in contact with the edge's endpoints. The ball pivots until it touches another scan point, forming another triangle. The ball-pivoting operation continues until all reachable edges have been tried, and then starts from another seed triangle, until all scan points have been considered.

Method and apparatus for reconstructing a surface using a ball-pivoting algorithm

A system and method is disclosed for constructing a digital model of an object. The system includes an imaging system for generating object surface scan data from a plurality of surface scans, the surface scan data having a first resolution and representing the object from a plurality of viewpoints. The imaging system further generates image data having a second, higher resolution than the surface scan data for representing the object from the plurality of viewpoints. The system further includes a data processor for iteratively registering the surface scan data for the plurality of surface scans, using the image data, and for reconstructing substantially seamless surface texture data for the model using weights that reflect a level of confidence in the data at a plurality of surface points.

High quality texture reconstruction from multiple scans

A method and system for deriving colors from photometric calculations with adjustment by a global color registration process. Information from a low spatial resolution mesh representation of the object is combined with higher resolution color images from a photometric system. The colors computed using the low spatial resolution mesh representation are made consistent from image to image such that, when the images are combined, the resultant image of the object exhibits substantially seamless, artifact-free surface color characteristics.

Method and apparatus for acquiring a set of consistent image maps to represent the color of the surface of an object

A method, system and computer program for obtaining a digital model of an object. The method includes steps of (a) generating a low spatial resolution numerical representation of an object, such as a triangular mesh representation; (b) generating higher spatial resolution images of the object using a photometric subsystem, having a camera and a lighting source; and (c) computing normals maps using the low resolution numerical representation to estimate a distance from the camera to points on the object and to adjust relative light source intensities so as to correct for uncertainties in distances and light source intensities. A feature of this method is that the computed normals maps are made consistent over the object.

Method and apparatus for acquiring normals maps consistent with low spatial resolution meshes

Disclosed are methods and apparatus for obtaining the shape of an object by observing silhouettes of the object. At least one point light source is placed in front of the object, thereby casting a shadow of the object on a translucent panel that is placed behind the object. A camera, or other imaging device, captures an image of the shadow from behind the translucent panel. The object's full silhouette is obtained from the image of the shadow as the region of the shadow is substantially darker than the region outside of the shadow. The full silhouette thus obtained may be processed by any suitable shape from silhouette algorithm, and thus objects are not limited in topological type. A color image of the object can optionally be obtained simultaneously with the shadow image using a camera placed on the same side of the object as the light source. Multiple silhouettes can be captured for one object position, reducing the number of rotations needed on a turntable system, and reducing the post-processing needed to register geometries obtained from multiple different positions.

System, method, and program product for acquiring accurate object silhouettes for shape recovery

A method and apparatus for retrieving and organizing data using a self-organizing map in a parallel transaction data base system. With this invention, input records of data are represented as n dimensional vectors. Each of these vectors then compressed by eliminating zeros in the components of these vectors. Then, the self-organizing map algorithm is applied to the compressed input records to group the records into a number of clusters, where each cluster comprises a number of records having common input parameters.

Scalable parallel algorithm for self-organizing maps with applications to sparse data mining problems

A method and system for obtaining and processing acquired images of an object to extract a small scale geometry (a bump map) of the object that is independent of object curvature. The method includes steps of (a) operating N (where N&gt;3) light sources and an image input device placed at a distance from the object such that different regions of the object are illuminated by each of the multiple light sources; (b) obtaining multiple images of the object, one for each of the light sources with the other light sources turned off; (c) processing the images to derive three images, each corresponding to a component of surface normals of the object relative to directions to three of the light sources; (d) removing an effect of large scale surface shape from the derived images of the surface normals by computing low spatial frequency images from the derived images; (e) for a section or sections of the images for which the small scale geometry is to be acquired, determining transformations from the surface normals represented by the low spatial frequency images to the normals of a planar surface; (f) applying the transformations to the derived surface normal images to obtain the normals of the small scale surface variations applied to a flat plane; (g) adjusting a spacing of the values for the normals to account for foreshortening due to curvature by expanding the distances using directional derivatives computed from the surface normals at each point in the image; and (h) obtaining regularly spaced images of new surface normals by sampling the spatially adjusted images onto a new, regularly spaced image.

Growing community of inventors

Mount Kisco, NY, United States of America

Holly Edith Rushmeier