A method of converting 2D to 3D video
A video and 3D technology, applied in the field of video processing, can solve the problems of long time, low efficiency and large time consumption.
Active Publication Date: 2021-10-22
ZHIZHUN ELECTRONICS SCI & TECH SHANGHAI
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, in the current film field, the technical difficulty of converting 2D to 3D is high, the efficiency is low, and the production process is complicated.
Today's general 2D to 3D technology first uses tracking software to track the camera, and imports the tracked camera information and corresponding video sequences into the 3D production software; thirdly, the model and animation are produced according to the position of the model in the scene in the image , which is equivalent to reconstructing scenes and animations, in which the production of models and animations takes a lot of time; then the existing images are mapped to the newly created animation scenes, and the entire scene is re-rendered, which also consumes a lot of time. The whole process Time-consuming and inefficient
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0027] see figure 1 and figure 2 , a method for converting 2D to 3D video, characterized in that, the following processing steps are adopted:
[0028] a. Introduce a single shot image sequence, use the displacement of the highly recognizable feature area from the first frame to the last frame in the planar image sequence, obtain the motion trajectory of many feature area blocks in the image sequence, reverse the spatial position and motion trajectory of the camera, and obtain multiple Image feature points: Assuming that the resolution size of the image is m, n, define the spatial coordinates of any point Source Point of the source image as Where z=0, x∈[-m / 2, m / 2], y∈[-n / 2, n / 2], the center point of the source image satisfies |f(x)|+|f(y)| = 0; Let the position of any feature point in the space be Where z=0, x∈(-m / 2, m / 2), y∈(-n / 2, n / 2), the center point of the plane passing through the feature point and parallel to the source image plane satisfies |g(x) |+|g(y)|=0;...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to the technical field of video processing, in particular to a method for converting 2D into 3D video. The motion trajectory of a feature region with high recognition degree in a plane image sequence is used to reverse the spatial position and motion trajectory of a camera to obtain an image. The feature points of the sequence in the space; according to the data of the camera motion trajectory and the displacement data of the feature points in the three-dimensional space, the error feature points are identified and corrected, and the accurate image sequence feature points are obtained; the distance between the different feature points and the camera is used. Calculate the black and white depth information of a single frame image; use the black and white depth information of a single frame image and the continuous information of the source image sequence to calculate the black and white depth information of the whole image sequence; make the corresponding area of the source image sequence and the black and white information sequence diagram The corresponding stereo separation is performed to realize the real three-dimensional space of the camera view, which greatly shortens the conversion time; and the feature points are unique, the conversion is accurate and efficient, and the processing method is simple.
Description
technical field [0001] The invention relates to the technical field of video processing, in particular to a method for converting 2D to 3D video. Background technique [0002] With the continuous advancement of technology, people have higher and higher requirements for movies, and the visual effects of 3D movies have been highly praised by the audience. Therefore, in order to obtain greater benefits, many investors and producers of 2D movies want to become 3D movies through corresponding post-production processing. [0003] However, in the current film field, the technical difficulty of converting 2D to 3D is high, the efficiency is low, and the production process is complicated. Today's general 2D to 3D technology first uses tracking software to track the camera, and imports the tracked camera information and corresponding video sequences into the 3D production software; thirdly, the model and animation are produced according to the position of the model in the scene in th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04N13/122H04N13/128H04N13/207H04N13/239H04N13/246H04N13/264H04N13/275
CPCH04N2013/0081
Inventor 林小军
Owner ZHIZHUN ELECTRONICS SCI & TECH SHANGHAI