6 results about "Face hallucination" patented technology

The invention belongs to the technical field of image super-resolution reconstruction, and discloses a face super-resolution method and system based on frequency domain self-calibration feature enhancement, and the method comprises the steps: firstly constructing multi-scale input through interpolation; then extracting deep features by using an encoder comprising a CNN-KAN hybrid module (MCKM), and fusing originally input face features to enhance multi-scale information mining; then, a fast Fourier adjustment module (FFAB) is used to realize optimization of face detail information in a frequency domain; and finally, dynamically fusing the multi-level features through a decoder and outputting a multi-scale reconstructed image. Meanwhile, a loss joint optimization model is reconstructed in combination with a multi-scale spatial domain and a frequency domain. According to the method, feature representation is enhanced through the MCKM, the model is optimized in the frequency domain by means of the FFAB, and the encoder-decoder features are collaboratively optimized by using the adaptive fusion module (AFM), so that the detail reduction precision and the structure fidelity of face image reconstruction are remarkably improved while the calculation efficiency is kept.

The application discloses a kind of based on multi-level supervision attention mechanism super network and random erasing data enhancement's occluded face image super resolution method, comprising: face region cutting, random erasing face content and size adjustment are carried out to public face dataset, construct low-resolution occluded face / high-resolution unoccluded face image pair dataset, and multiple data enhancements are carried out to training set;Multi-level supervision attention mechanism face image super resolution network based on face structure priori guide is constructed;Multi-level supervision attention mechanism face image super resolution network based on face structure priori guide is trained on training set;Low-resolution occluded face image in test set is carried out super resolution.This application overcomes the existing face super resolution method in processing accompanying occlusion input low-resolution face image when result image structure distortion, the problem of detail accompanying artificial artifact, can reconstruct structure complete, accurate, high-resolution face image with high fidelity.

The application discloses a non-aligned face image super-resolution method based on a layered structure perception space conversion network, and comprises the following steps: performing random angle rotation, face region cutting and size adjustment on a public face dataset, constructing a non-aligned low-resolution face / aligned high-resolution face image pair dataset, and dividing a training set and a test set; constructing a non-aligned face image super-resolution model based on a layered structure perception space conversion network; training the non-aligned face image super-resolution model based on the layered structure perception space conversion network on the training set; and performing super-resolution on non-aligned low-resolution face images in the test set. The non-aligned face image super-resolution model constructed by the application can overcome the problems of structure distortion and details accompanying artificial artifacts of a generated face image under the influence of a non-aligned factor in an existing face super-resolution method, so that the application can reconstruct an aligned and high-fidelity high-resolution face image.

The present invention relates to the fields of image processing and deep learning technology, and discloses a progressive facial super-resolution method and system based on artistic prior knowledge. The system comprises: an image encoding module for extracting multi-scale features from an input low-resolution facial image and outputting latent features; a structure learning module for guiding basic morphological restoration; a detail completion module for texture restoration; a mask fusion module for integrating coarse and fine granularity features; and a super-resolution decoder for receiving the fused features and reconstructing a high-resolution facial image. The present invention can effectively enhance the fidelity of key facial features, ensuring the consistency and naturalness of local features while improving overall image clarity. This significantly improves the unreality and instability caused by prior art techniques that rely on speculative generation, thereby improving the reconstruction quality and application reliability of facial images.

The present invention discloses a face super-resolution method and system based on a dual guided diffusion model. The method comprises the following steps: collecting low-resolution non-frontal face images and high-resolution frontal face images to construct training data pairs; preliminarily restoring the low-resolution non-frontal face images to obtain rough frontal face images; mapping the face images in pixel space to implicit space, enabling a diffusion model to be calculated in the implicit space, pre-training the unconditional diffusion model, using the training results as initialization parameters of the diffusion model, and freezing the encoder of a denoising network; extracting facial prior features from the rough frontal face images, and capturing the spatial and semantic correlations between the facial prior features and denoising features through a hybrid cross-attention mechanism; extracting facial identity coding information and embedding it into a denoising network; initializing a Gaussian noise map, iteratively denoising using the trained diffusion model, mapping the denoising results in the implicit space to the pixel space, and finally reconstructing a high-resolution frontal face image.

A face super-resolution method based on visual language prior art of the application comprises the following steps: step one, sending a low-resolution face image into a pre-trained visual-language large model to extract a visual-language multi-element representation; step two, constructing a visual-language prior art auxiliary face super-resolution network to fuse visual-language prior art information; step three, sending the low-resolution face image and the visual-language multi-element representation extracted in step one into the network in step two to obtain a super-resolution result and a restored high-quality face image. Compared with existing mainstream face super-resolution methods (FSRNet, DIC, SISN, SFMNet, FaceFormer and WFEN), the face image restored by the application performs better in both objective evaluation indexes and subjective visual quality.