Method and device for image bit-depth expansion based on combination frame

Abstract

The present invention discloses a method and device for image bit-depth expansion based on a combination frame. The traditional de-banding effect algorithm and the learning algorithm based on a deep network are fused to remove the unnatural effect of an image flat region and more realistically recover the value information of deleted bits; and the method comprises extraction of the image flat region, the flat region bit-depth expansion based on local adaptive pixel value regulation and the non-flat region bit depth expansion based on the convolutional neural network. The method based on learning is employed to solve the vivid bit deletion recovery problem through training of an efficient deep network; and moreover, the method effectively inhibits the unnatural effects such as banding effect, the ringing effect, flat noise and the like of a flat region aiming at usage of a simple and robust local adaptive pixel value regulation method at the flat region so as to improve the subjective visual sense quality of the flat region.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to image bit depth extension and enhancement processing technology, in particular to an image bit depth extension method and device based on a hybrid framework, which combines adaptive pixel value adjustment and convolutional neural network based reconstruction technique. Background technique [0002] Image bit-depth expansion (Bit-Depth Expansion) refers to the recovery of high-bit-depth images from low-bit-depth images. The bit depth of an image (Bit-Depth) is the number of binary bits in the value of each pixel in the image. For example, the value range of a pixel in an 8-bits image is 0 to 255 (28). The higher the bit depth of the image, the more delicate the brightness changes can be reflected. The bit depth that the human eye can perceive is between 12 and 14 bits, so we often feel that the image seen through the 8bits display is different from the picture seen by the...

AI Technical Summary

Problems solved by technology

However, the current bit-depth extension methods are mostly traditional non-learning methods, which use fixed strategies to fill in the missing bit information, but the ability to reconstruct the real value of the missing bit is weak, and at the same time, it often removes the banding effect. Causes loss of high-frequency detail in non-flat areas

Existing methods are difficult to restore high-bit-depth images without unnatural effects and high-frequency texture details with higher fidelity from low-bit-depth images

Images