Search

In this paper, a full-reference image quality assessment (FR-IQA) model based on deep meta-learning and Conformer is proposed. We combine the Conformer architecture with a Siamese network to extract the feature vectors of the reference and distorted images and calculate the similarity of these feature vectors as the predicted score of the image. We use meta-learning to help the model identify different types of image distortion. First, because the information taken as input by the human visual system (HVS) ranges in scale from local to global, we use a Conformer network as a feature extractor to obtain the global and local features of the pristine and distorted images and use a Siamese network to reduce the number of parameters in our model. Second, we use meta-learning to carry out bilevel gradient descent from the query set to the support set in the training stage and fine-tune the model parameters on a few images with unknown distortion types in the testing stage to improve the generalization ability of the model. Experiments show that our method is competitive with existing FR-IQA methods on three standard IQA datasets.

As social media communication develops, reliable multimedia quality evaluation indicators have become a prerequisite for enriching user experience services. In this paper, we propose a multiscale spatiotemporal pyramid attention (SPA) block for constructing a blind video quality assessment (VQA) method to evaluate the perceptual quality of videos. First, we extract motion information from the video frames at different temporal scales to form a feature pyramid, which provides a feature representation with multiple visual perceptions. Second, an SPA module, which can effectively extract multiscale spatiotemporal information at various temporal scales and develop a cross-scale dependency relationship, is proposed. Finally, the quality estimation process is completed by passing the extracted features obtained from a network of multiple stacked spatiotemporal pyramid blocks through a regression network to determine the perceived quality. The experimental results demonstrate that our method is on par with the state-of-the-art approaches. The source code necessary for conducting groundbreaking scientific research is accessible online https://github.com/Land5cape/SPBVQA.

In this paper, an end-to-end blind image quality assessment (BIQA) model based on feature fusion with an attention mechanism is proposed. We extracted the multilayer features of the image and fused them based on the attention mechanism; the fused features are then mapped into score, and the image quality assessment without reference is realized. First, because the human visual perception system hierarchically approaches the input information from local to global, we used three different neural networks to extract physically meaningful image features, and we use modified VGG19 and modified VGG16 to extract the substrate texture information and the local information of the edges, respectively. Meanwhile, we use the resNet50 to extract high-level global semantic information. Second, to take full advantage of multilevel features and avoid monotonic addition in hierarchical feature fusion, we adopt an attention-based feature fusion mechanism that combines the global and local contexts of the features and assigns different weights to the features to be fused, so that the model can perceive richer types of distortion. Experimental findings on six standard databases show that our approach yields improved performance.