Abstract: Scenes reconstruction may be performed using videos that capture the scenes at high resolution and frame rate. Scene reconstruction may be associated with determining camera orientation and/or location (“camera pose”) throughout the video, three-dimensional coordinates of feature points detected in frames of the video, and/or other information. Individual videos may have multiple frames. Feature points may be detected in, and tracked over, the frames. Estimations of camera pose may be made for individual subsets of frames. One or more estimations of camera pose may be determined as fixed estimations. The estimated camera poses for the frames included in the subsets of frames may be updated based on the fixed estimations. Camera pose for frames not included in the subsets of frames may be determined to provide globally consistent camera poses and three-dimensional coordinates for feature points of the video.

Abstract: Scenes reconstruction may be performed using videos that capture the scenes at high resolution and frame rate. Scene reconstruction may be associated with determining camera orientation and/or location (“camera pose”) throughout the video, three-dimensional coordinates of feature points detected in frames of the video, and/or other information. Individual videos may have multiple frames. Feature points may be detected in, and tracked over, the frames. Estimations of camera pose may be made for individual subsets of frames. One or more estimations of camera pose may be determined as fixed estimations. The estimated camera poses for the frames included in the subsets of frames may be updated based on the fixed estimations. Camera pose for frames not included in the subsets of frames may be determined to provide globally consistent camera poses and three-dimensional coordinates for feature points of the video.

Abstract: Scenes reconstruction may be performed using videos that capture the scenes at high resolution and frame rate. Scene reconstruction may be associated with determining camera orientation and/or location (“camera pose”) throughout the video, three-dimensional coordinates of feature points detected in frames of the video, and/or other information. Individual videos may have multiple frames. Feature points may be detected in, and tracked over, the frames. Estimations of camera pose may be made for individual subsets of frames. One or more estimations of camera pose may be determined as fixed estimations. The estimated camera poses for the frames included in the subsets of frames may be updated based on the fixed estimations. Camera pose for frames not included in the subsets of frames may be determined to provide globally consistent camera poses and three-dimensional coordinates for feature points of the video.

Abstract: A system, method, and computer program product are provided for efficiently ray tracing micropolygon or other highly complex geometry. In operation, a first hierarchy of a plurality of objects is established. Additionally, rays are traced using the first hierarchy to efficiently identify which of the plurality of objects are potentially intersected. Furthermore, at least one of the potentially intersected objects are decomposed, on-demand, into a set of subobjects, each set of subobjects corresponding to one of the at least one of the potentially intersected objects. Still yet, a second hierarchy is established for at least one of the set of subobjects, the second hierarchy being determined by a connectivity of subobjects in an associated set of subobjects in order to accelerate ray tracing.

Abstract: A system (100) for scanning a three-dimensional object (150) comprises a device for illuminating a plane (110); an imaging sensor (120); and a transparent container (130) for immersing the object (150) in a participating medium (140).

Abstract: A system, method, and computer program product are provided for efficiently ray tracing micropolygon or other highly complex geometry. In operation, a first hierarchy of a plurality of objects is established. Additionally, rays are traced using the first hierarchy to efficiently identify which of the plurality of objects are potentially intersected. Furthermore, at least one of the potentially intersected objects are decomposed, on-demand, into a set of subobjects, each set of subobjects corresponding to one of the at least one of the potentially intersected objects. Still yet, a second hierarchy is established for at least one of the set of subobjects, the second hierarchy being determined by a connectivity of subobjects in an associated set of subobjects in order to accelerate ray tracing.

Abstract: A system (100) for scanning a three-dimensional object (150) comprises a device for illuminating a plane (110); an imaging sensor (120); and a transparent container (130) for immersing the object (150) in a participating medium (140).