科研成果详情

In deep learning-based no-reference image quality assessment (NR-IQA) methods, the absence of reference images limits their ability to assess content fidelity, making it difficult to distinguish between original content and distortions that degrade quality. To address this issue, we propose a quality adversarial learning framework emphasizing both content fidelity and prediction accuracy. The main contributions of this study are as follows: First, we investigate the importance of content fidelity, especially in no-reference scenarios. Second, we propose a quality adversarial learning framework that dynamically adapts and refines the image quality assessment process on the basis of the quality optimization results. The framework generates adversarial samples for the quality prediction model, and simultaneously, the quality prediction model optimizes the quality prediction model by using these adversarial samples to maintain fidelity and improve accuracy. Finally, we demonstrate that by employing the quality prediction model as a loss function for image quality optimization, our framework effectively reduces the generation of artifacts, highlighting its superior ability to preserve content fidelity. The experimental results demonstrate the validity of our method compared with state-of-the-art NR-IQA methods. The code is publicly available at the following website: https://github.com/Land5cape/QAL-IQA.