Stereo 3D Technologies
2D–to–Stereo 3D Conversion Using Depth Maps
For 2D–to–stereo 3D conversion, YUVsoft’s products explicitly use depth maps. Such approaches have proven their practicality and versatility in a number of projects for 2D-to-3D conversion of theatrical movies. Explicit depth maps greatly simplify depth grading and dynamic change of parallax when creating different releases.
The resulting stereo video is generated from semiautomatically constructed depth maps and original 2D video.
The key steps of our 2D-to-2D+Depth conversion process are
- Automatically create plausible depth maps for a scene
- Select and edit the best depth maps for a few frames, making these frames key frames; the depth map for other frames is mostly generated automatically
- Rotoscope critical foreground objects where necessary
- Use depth propagation to protract semiautomatically generated depth maps of selected frames to entire scene
- Refine depth using special brushes or other manual editing tools and repeat propagation until acceptable quality is achieved; results are evaluated by generating stereo for intermediate depth maps
Stereo Video Analysis and Conversion
Content filmed in stereo is becoming more widespread, and it requires special processing functions.
We offer the following technologies for stereo video enhancement and conversion:
- Automatic correction of global mismatches in geometry and color
- Automatic disparity map estimation
- Objective and subjective quality analysis
- Automatic stereo-to-multiview conversion