Face hallucination method and system of global-local separation attention mechanism

Abstract

The invention discloses a face hallucination method and system based on a global-local separation attention mechanism. The method comprises the following steps: down-sampling a high-resolution face image to a target low-resolution face image; segmenting the target low-resolution image into blocks so as to extract a rough face feature map after mutually overlapped image blocks are obtained; constructing a separation attention network as a fine feature extractor, inputting the rough face features into the separation attention network to obtain a fine face feature map, wherein the separation attention network comprises a plurality of global-local separation attention groups, each global-local separation attention group generates two pieces of local attention and uses one global attention module to fuse different local attention, so that the local attention interacts across the feature groups, and the global attention of the network is realized; up-sampling the obtained face fine feature map; and reconstructing the up-sampled face feature map into a high-resolution face image of the target. According to the method, a face hallucination image with higher quality can be generated.

Description

technical field [0001] The invention belongs to the field of computer vision human face super-resolution, and more specifically relates to a method and system for human face super-resolution based on a global-local separation attention mechanism. Background technique [0002] Face super-resolution (face hallucination) is a special field of super-resolution (Super-Resolution, SR), which is a method to infer high-resolution images from input low-resolution (Low Resolution, LR) face images. (High Resolution, HR) image technology, which can significantly enhance the details of low-resolution face images. In real-world surveillance scenarios, the distance between the imaging sensor and the face is often too large, resulting in low-resolution face images. Using face super-resolution to restore high-resolution face images is helpful for target person identification. This method plays an important role in many applications such as face detection, face recognition and analysis. ...

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention proposes a face super-resolution method and system based on a global-local separation attention mechanism, which solves the problem that the current face super-resolution reconstruction algorithm cannot use both global and local Attention mechanism, a technical problem that leads to certain limitations in the performance of face image reconstruction

Images