Video face hallucination method and device based on component decomposition

Abstract

The invention discloses a video face hallucination method and a device based on component decomposition, which can improve the performance of the face hallucination in a low-resolution face video. The method comprises steps: as for each frame of image in the low-resolution face video for face hallucination, the face part in the frame of image is decomposed according to a face structure, and each face part obtained through decomposition is cut into image blocks; as for each image block obtained through cutting, a preset number of nearest neighbor image blocks for the image block is acquired from a preset image block library; as for each frame of image in the low-resolution face video, the nearest neighbor image blocks are used to adopt a local constraint-based neighborhood embedding method to rebuild the image block obtained through cutting the frame of image, high-resolution image blocks are obtained, and through combining the high-resolution image blocks, a target high-resolution image is obtained; and through combining each target high-resolution image, a target high-resolution face video is obtained.

Description

technical field [0001] The invention relates to the technical field of image synthesis and reconstruction, in particular to a method and device for video human face phantom construction based on component decomposition. Background technique [0002] Face phantom refers to reconstructing a corresponding high-resolution face image from an input single-frame low-resolution face image or a multi-frame low-resolution face image sequence. Since face pictures have specific structural features, some methods of face phantom reconstruction model the face structure to perform face super-resolution reconstruction. [0003] Wang and Tang proposed a global face illusion algorithm based on principal component analysis. First, use principal component analysis to project the low-resolution image library to the low-resolution feature space, and then calculate the projection coefficient of the low-resolution image in the low-resolution feature space, and assume that the high-resolution projec...

AI Technical Summary

Problems solved by technology

Because this kind of method contains the step of aligning the face pictures, it is difficult to achieve the desired effect when the alignment is insufficient or the faces of different angles and poses are input.

[0005] Because most of the current face illusion methods require face images to be highly aligned or relatively similar, when there is a large difference between the test image and the training image, the performance of the algorithm will drop significantly, and the current algorithm is also difficult to apply to human faces. In videos with changing facial postures

Images