{"ID":2891166,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17182","arxiv_id":"2507.17182","title":"Hierarchical Fusion and Joint Aggregation: A Multi-Level Feature Representation Method for AIGC Image Quality Assessment","abstract":"The quality assessment of AI-generated content (AIGC) faces multi-dimensional challenges, that span from low-level visual perception to high-level semantic understanding. Existing methods generally rely on single-level visual features, limiting their ability to capture complex distortions in AIGC images. To address this limitation, a multi-level visual representation paradigm is proposed with three stages, namely multi-level feature extraction, hierarchical fusion, and joint aggregation. Based on this paradigm, two networks are developed. Specifically, the Multi-Level Global-Local Fusion Network (MGLF-Net) is designed for the perceptual quality assessment, extracting complementary local and global features via dual CNN and Transformer visual backbones. The Multi-Level Prompt-Embedded Fusion Network (MPEF-Net) targets Text-to-Image correspondence by embedding prompt semantics into the visual feature fusion process at each feature level. The fused multi-level features are then aggregated for final evaluation. Experiments on benchmarks demonstrate outstanding performance on both tasks, validating the effectiveness of the proposed multi-level visual assessment paradigm.","short_abstract":"The quality assessment of AI-generated content (AIGC) faces multi-dimensional challenges, that span from low-level visual perception to high-level semantic understanding. Existing methods generally rely on single-level visual features, limiting their ability to capture complex distortions in AIGC images. To address thi...","url_abs":"https://arxiv.org/abs/2507.17182","url_pdf":"https://arxiv.org/pdf/2507.17182v1","authors":"[\"Linghe Meng\",\"Jiarun Song\"]","published":"2025-07-23T04:12:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}