A method for three-dimensional (3D) modeling using two-dimensional (2D) image data includes obtaining a first image of an object oriented in a first direction and a second image of the object oriented in a second direction, determining a plurality of feature points of the object in the first image, and determining a plurality of matching feature points of the object in the second image that correspond to the plurality of feature points of the object in the first image. The method further includes calculating similarity values between the plurality of feature points and the corresponding plurality of matching feature points, calculating depth values of the plurality of feature points, calculating weighted depth values based on the similarity values and depth values, and performing 3D modeling of the object based on the weighted depth values.

A method for three-dimensional (3D) modeling using two-dimensional (2D) image data includes obtaining a first image of an object oriented in a first direction and a second image of the object oriented in a second direction, determining a plurality of feature points of the object in the first image, and determining a plurality of matching feature points of the object in the second image that correspond to the plurality of feature points of the object in the first image. The method further includes calculating similarity values between the plurality of feature points and the corresponding plurality of matching feature points, calculating depth values of the plurality of feature points, calculating weighted depth values based on the similarity values and depth values, and performing 3D modeling of the object based on the weighted depth values.

Apparatus comprises a camera configured to capture images of a user in a scene; a depth detector configured to capture depth representations of the scene, the depth detector comprising an emitter configured to emit a non-visible signal; a mirror arranged to reflect at least some of the non-visible signal emitted by the emitter to one or more features within the scene that would otherwise be occluded by the user and to reflect light from the one or more features to the camera; a pose detector configured to detect a position and orientation of the mirror relative to at least one of the camera and depth detector; and a scene generator configured to generate a three-dimensional representation of the scene in dependence on the images captured by the camera and the depth representations captured by the depth detector and the pose of the mirror detected by the pose detector.

Presently disclosed is a method for co-segmenting three-dimensional models represented by sparse and low-rank feature, comprising: pre-segmenting each three-dimensional model of a three-dimensional model class to obtain three-dimensional model patches for the each three-dimensional model; constructing a histogram for the three-dimensional model patches of the each three-dimensional model to obtain a patch feature vector for the each three-dimensional model; performing a sparse and low-rank representation to the patch feature vector for the each three-dimensional model to obtain a representation coefficient and a representation error of the each three-dimensional model; determining a confident representation coefficient for the each three-dimensional model according to the representation coefficient and the representation error of the each three-dimensional model; and clustering the confident representation coefficient of the each three-dimensional model to co-segment the each three-dimensional model respectively.

Presently disclosed is a method for co-segmenting three-dimensional models represented by sparse and low-rank feature, comprising: pre-segmenting each three-dimensional model of a three-dimensional model class to obtain three-dimensional model patches for the each three-dimensional model; constructing a histogram for the three-dimensional model patches of the each three-dimensional model to obtain a patch feature vector for the each three-dimensional model; performing a sparse and low-rank representation to the patch feature vector for the each three-dimensional model to obtain a representation coefficient and a representation error of the each three-dimensional model; determining a confident representation coefficient for the each three-dimensional model according to the representation coefficient and the representation error of the each three-dimensional model; and clustering the confident representation coefficient of the each three-dimensional model to co-segment the each three-dimensional model respectively.

A non-transitory computer-readable recording medium stores a voxelization program that causes a computer to execute a process. The process includes voxelizing a three-dimensional shape to generate a first voxel structure corresponding to the three-dimensional shape, specifying, in a case where lines perpendicular to respective faces of a cube or a cuboid containing the generated first voxel structure are extended from the respective faces toward inside the cube or the cuboid until the lines hit the first voxel structure, a region outside an outer periphery of the first voxel structure according to whether at least lines extended from three faces orthogonal to each other intersect, and setting the specified outside region as a second voxel structure, and performing inversion to invert a region of the voxel structures and a region not set as a voxel in the cube or the cuboid.

A computer readable storage medium stores a facetization processing program that causes a computer to execute a process. The process includes: voxelizing a three-dimensional shape; generating first voxels corresponding to the three-dimensional shape; specifying an area surrounded by the generated first voxels; setting the specified area as voxels to generate second voxels; and facetizing third voxels at a boundary between at least one of the first voxels and a non-voxel area, and the second voxels and the non-voxel area.

A computer readable recording medium stores a program that causes a computer to execute a process. The process includes: voxelizing a three-dimensional model to generate a voxel model; performing inversion processing on an area in three-dimensional space including the generated voxel model to invert an area set as voxels and an area not set as voxels; extracting an area including specific two points from the area set as voxels after the inversion processing, the area to be extracted allowing center of a specific sphere having a predetermined size to pass anywhere therein; determining a shortest path between the specific two points within the extracted area; and outputting the shortest path.

A shape generation system can generate a three-dimensional (3D) model of an object from a two-dimensional (2D) image of the object by projecting vectors onto light cones created from the 2D image. The projected vectors can be used to more accurately create the 3D model of the object based on image element (e.g., pixel) values of the image.

Embodiments of the present invention describe predictively reconstructing a physical event using augmented reality. Embodiments describe, identifying relative states of objects located in a physical event area by using video analysis to analyze collected video feeds from the physical event area before and after a physical event involving at least one of the objects, creating a knowledge corpus including the video analysis and the collected video feeds associated with the physical event and historical information, and capturing data, by a computing device, of the physical event area. Additionally, embodiments describe identifying possible precursor events based on the captured data and the knowledge corpus, and generating a virtual reconstruction of the physical event using the possible precursor events, displaying, by the computing device, the generated virtual reconstruction of the predicted physical event, wherein the displayed virtual reconstruction of the predicted physical event overlays an image of the physical event area.