| 摘要 |
The present disclosure provides a method for converting a Two-Dimensional image into a Three-Dimensional image, comprising: obtaining high-frequency components and low-frequency component of the current frame, and high-frequency components of the reference frame; establishing triangular geometric models in the three directions of horizontal, vertical and diagonal, respectively; performing a motion search on the high-frequency components of the reference frame in the three directions of horizontal, vertical and diagonal, respectively, so as to obtain motion vectors in the corresponding directions, and calculating depth variations of the corresponding directions according to the motion vectors in the corresponding directions; performing an interpolating operation on the triangular geometric models in the three directions of horizontal, vertical and diagonal, respectively, according to the depth variations in the corresponding directions, so as to obtain high-frequency depth graphs in the corresponding directions; and completing a filtering reconstruction by performing an inversion wavelet transform on the high-frequency depth graphs in the three directions of horizontal, vertical and diagonal and the low-frequency component of the current frame, respectively, so as to construct a three-dimensional video image. With the present disclosure, a conversion to the 3D image from the 2D image may be realized. |
| 主权项 |
1. A method for converting a Two-Dimensional video image into a Three-Dimensional video image, comprising:
in a step A, performing, by a processing unit, a lifting wavelet transform on a current frame and a reference frame of a two-dimensional video image signal, respectively, to obtain high-frequency components and low-frequency component of the current frame, and high-frequency components of the reference frame, the high-frequency components comprise high-frequency components in three directions of horizontal, vertical and diagonal; in a step B, establishing, by the processing unit, triangular geometric models in the three directions of horizontal, vertical and diagonal, respectively, according to the high-frequency components of the current frame; in a step C, performing, by the processing unit, a motion search on the high-frequency components of the reference frame in the three directions of horizontal, vertical and diagonal, respectively, by using the triangular geometric models of the current frame, so as to obtain motion vectors in the corresponding directions, and calculating depth variations in the corresponding directions according to the motion vectors in the corresponding directions; in a step D, performing, by the processing unit, an interpolating operation on the triangular geometric models in the three directions of horizontal, vertical and diagonal, respectively, according to the depth variations in the corresponding directions, so as to obtain high-frequency depth graphs in the corresponding directions; and in a step E, completing, by the processing unit, a filtering reconstruction by performing an inversion wavelet transform on the high-frequency depth graphs in the three directions of horizontal, vertical and diagonal and the low-frequency component of the current frame, respectively, so as to construct a three-dimensional video image. |
