A deep super-resolution image filtering processing method
A super-resolution and image filtering technology, applied in image data processing, image enhancement, graphics and image conversion, etc., can solve the problem of low efficiency of image smoothing filtering, achieve fast image smoothing filtering, improve image filtering accuracy, reduce effect of noise
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0027] Embodiment one: if figure 1 As shown, Embodiment 1 of the present invention discloses a depth super-resolution image filtering processing method, including the following steps:
[0028] S1. Input the image I to be processed;
[0029] S2. Bring the deep super-resolution image filtering framework into the image I to obtain the upsampled dense depth image D of the image I F ; Wherein, the depth super-resolution image filtering framework is specifically shown in formula 1:
[0030]
[0031] D. F is an upsampled dense depth image, F(D) is a filtered image with upsampled depth values, and F(M) is a filtered image without upsampled depth processing. The processing steps of the filtered image F(D) of the upsampled depth value are: S21, calculate the upsampled depth value D(P) of the image I at P; S22, bring the upsampled depth value D(P) into the filter The filtered image F(D) of the upsampled depth value is obtained in the device F(x). In step S21, the specific calcula...
Embodiment 2
[0038] Embodiment two: if figure 2 As shown, Embodiment 2 of the present invention also discloses a method for processing depth super-resolution image filtering, including the following steps:
[0039] S1. Input the image I to be processed;
[0040] S2. Replace the depth super-resolution image filtering framework in Embodiment 1 of the present invention with the depth super-resolution image filtering model, and bring the depth super-resolution image filtering model into image I to obtain an upsampled dense depth image of image I D. F , where the depth super-resolution image filtering model is specifically shown in formula 3:
[0041]
[0042] (a i ,b i ,c i ) represents the parameters of the i-th surface model, Denote the depth of pixel p by pixel coordinates [x, y], f is the spatial Gaussian filter kernel, g is the range filter kernel centered on the RGB image value at p, and Ω is the spatial support of kernel f.
[0043] The establishment of this deep super-resol...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap