A characteristic matching method for compressing video super-resolution based on learning
A super-resolution and feature matching technology, applied in digital video signal modification, television, image enhancement, etc., can solve problems affecting matching accuracy, and achieve the effect of improving matching accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] The invention provides a learning-based feature matching method for compressed video super-resolution when there is quantization noise. The basic principle is to use the characteristics that the low-frequency part of the frequency domain is less affected by quantization in the compressed video, and the quantization step size is known, and the low-frequency part is selected for average quantization noise compensation as a matching feature.
[0019] The present invention will be described below in conjunction with an embodiment of an image pyramid-based face super-resolution (phantom face) method. The advantages and characteristics of the present invention are illustrated by the detailed description of the embodiments, and the implementation method thereof will be clearer to those skilled in the art. However, the scope of the present invention is not limited to the embodiments disclosed in the description, and the present invention also It can be implemented in other form...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 