{"ID":2894163,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.12687","arxiv_id":"2507.12687","title":"TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets","abstract":"Image Quality Assessment (IQA) models aim to predict perceptual image quality in alignment with human judgments. No-Reference (NR) IQA remains particularly challenging due to the absence of a reference image. While deep learning has significantly advanced this field, a major hurdle in developing NR-IQA models is the limited availability of subjectively labeled data. Most existing deep learning-based NR-IQA approaches rely on pre-training on large-scale datasets before fine-tuning for IQA tasks. To further advance progress in this area, we propose a novel approach that constructs a custom dataset using a limited number of reference content images and introduces a no-reference IQA model that incorporates both content and quality features for perceptual quality prediction. Specifically, we train a quality-aware model using contrastive triplet-based learning, enabling efficient training with fewer samples while achieving strong generalization performance across publicly available datasets. Our repository is available at https://github.com/rajeshsureddi/triqa.","short_abstract":"Image Quality Assessment (IQA) models aim to predict perceptual image quality in alignment with human judgments. No-Reference (NR) IQA remains particularly challenging due to the absence of a reference image. While deep learning has significantly advanced this field, a major hurdle in developing NR-IQA models is the li...","url_abs":"https://arxiv.org/abs/2507.12687","url_pdf":"https://arxiv.org/pdf/2507.12687v1","authors":"[\"Rajesh Sureddi\",\"Saman Zadtootaghaj\",\"Nabajeet Barman\",\"Alan C. Bovik\"]","published":"2025-07-16T23:43:12Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":612098,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2894163,"paper_url":"https://arxiv.org/abs/2507.12687","paper_title":"TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets","repo_url":"https://github.com/rajeshsureddi/triqa","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}