| CPC G06T 17/20 (2013.01) [G06T 7/12 (2017.01); G06T 7/62 (2017.01); G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 10/46 (2022.01)] | 18 Claims |

|
1. A method performed by an electronic device for generating a three-dimensional model, the method comprising:
identifying, by the electronic device, at least one object, captured by a camera of the electronic device, which is associated with a region of interest (ROI) based on an objectness score;
performing, by the electronic device, a coarse semantic segmentation on the identified at least one object;
deriving, by the electronic device, a connected contour for the identified at least one object, the connected contour using a plurality of anchor points;
configuring, by the electronic device, at least one outer and inner contours based on a delaunay triangulation technique, the outer contour being an outline of an outside of the identified at least one object and the inner contour being an outline inside the identified at least one object;
filtering, by the electronic device, triangles of the at least one outer and inner contours with a centroid pixel in a black region;
assigning a height parameter based on a distance of at least one pixel in at least one intermediate contour of the at least one object; and
configuring, by the electronic device, the at least one object with a three-dimensional mesh, wherein a texture mapping is performed on the at least one object to generate the three-dimensional model of the captured at least one object.
|