Gaussian pyramid and anisotropic filtering-based image depth of field rendering method
A Gaussian pyramid and anisotropic technology, applied in the field of image depth rendering based on Gaussian pyramid and anisotropic filtering, can solve the problems of color leakage, low resolution of depth image, black noise, jagged distortion, etc., and achieve a good subjective image Quality, the effect of reducing the complexity of the algorithm
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0039] The flow chart of this algorithm is as follows figure 1 shown.
[0040] by figure 2 The image without depth of field effect shown in is taken as an example to illustrate the implementation steps of the algorithm. figure 2 From the Middlebury binocular dataset, image 3 yes figure 2 The corresponding depth image.
[0041]Utilize the method described in the present invention to process image, at first establish down-sampling Gaussian pyramid to depth map, carry out up-sampling operation from the image of the 4th layer, select each point to replace the black noise point in original depth map, obtain the depth map after reconstruction, The result is as Figure 4 shown. Using the optical model of the depth of field to calculate the size of the circle of confusion at each point in the scene, the result is as follows Figure 5 shown. Perform isotropic Gaussian filtering on the focus area of the diffusion circle image, the result is as follows Figure 6 shown. Th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com