{"ID":2823397,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00225","arxiv_id":"2601.00225","title":"Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions","abstract":"Blind Image Quality Assessment (BIQA) has advanced significantly through deep learning, but the scarcity of large-scale labeled datasets remains a challenge. While synthetic data offers a promising solution, models trained on existing synthetic datasets often show limited generalization ability. In this work, we make a key observation that representations learned from synthetic datasets often exhibit a discrete and clustered pattern that hinders regression performance: features of high-quality images cluster around reference images, while those of low-quality images cluster based on distortion types. Our analysis reveals that this issue stems from the distribution of synthetic data rather than model architecture. Consequently, we introduce a novel framework SynDR-IQA, which reshapes synthetic data distribution to enhance BIQA generalization. Based on theoretical derivations of sample diversity and redundancy's impact on generalization error, SynDR-IQA employs two strategies: distribution-aware diverse content upsampling, which enhances visual diversity while preserving content distribution, and density-aware redundant cluster downsampling, which balances samples by reducing the density of densely clustered areas. Extensive experiments across three cross-dataset settings (synthetic-to-authentic, synthetic-to-algorithmic, and synthetic-to-synthetic) demonstrate the effectiveness of our method. The code is available at https://github.com/Li-aobo/SynDR-IQA.","short_abstract":"Blind Image Quality Assessment (BIQA) has advanced significantly through deep learning, but the scarcity of large-scale labeled datasets remains a challenge. While synthetic data offers a promising solution, models trained on existing synthetic datasets often show limited generalization ability. In this work, we make a...","url_abs":"https://arxiv.org/abs/2601.00225","url_pdf":"https://arxiv.org/pdf/2601.00225v1","authors":"[\"Aobo Li\",\"Jinjian Wu\",\"Yongxu Liu\",\"Leida Li\",\"Weisheng Dong\"]","published":"2026-01-01T06:11:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":605495,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2823397,"paper_url":"https://arxiv.org/abs/2601.00225","paper_title":"Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions","repo_url":"https://github.com/Li-aobo/SynDR-IQA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}