High-magnification super-resolution method based on double transform domain
A super-resolution, double-transform technology, applied in the field of computer vision, can solve problems such as unsatisfactory high-magnification reconstruction results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0045]1) Turn a high-magnification problem into a multi-level small-magnification cascade problem. For each level of small-magnification super-resolution problem, use equation (1) to model:
[0046]
[0047]
[0048]Among them, let F(α)=ED(x,y)+λ1ETR (x,z)+λ2ESR (x,z),x∈Rn, Y∈Rm,z∈RnThey are the vectorized restored depth map, the vectorized low-resolution depth map and the vectorized high-resolution color map, ED(x,y) is the data item, ETR (x, z) is the regular term in the transform domain, ESR (x,z) is the regular term of the spatial domain, λ1And λ2Is the weight parameter to balance each item, min represents the minimum value,Represents the value of the variable x when the following formula is minimized; H represents the synthesis operator of fuzzy and sampling, αiRepresents block xiIn the dictionaryCoefficient under,Represents block xiThe dictionary corresponding to the type of block, xiIs the image block with the center at i in the depth map x; αqIs block xiThe qth similar block xi,q The...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


