{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-probabilistic-quality-representation","title":"A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction","arxiv_id":"1708.08190","date":"2017-08-28","proceeding":null,"authors":["Hui Zeng","Lei Zhang","Alan C. Bovik"],"abstract":"Blind image quality assessment (BIQA) remains a very challenging problem due\nto the unavailability of a reference image. Deep learning based BIQA methods\nhave been attracting increasing attention in recent years, yet it remains a\ndifficult task to train a robust deep BIQA model because of the very limited\nnumber of training samples with human subjective scores. Most existing methods\nlearn a regression network to minimize the prediction error of a scalar image\nquality score. However, such a scheme ignores the fact that an image will\nreceive divergent subjective scores from different subjects, which cannot be\nadequately represented by a single scalar number. This is particularly true on\ncomplex, real-world distorted images. Moreover, images may broadly differ in\ntheir distributions of assigned subjective scores. Recognizing this, we propose\na new representation of perceptual image quality, called probabilistic quality\nrepresentation (PQR), to describe the image subjective score distribution,\nwhereby a more robust loss function can be employed to train a deep BIQA model.\nThe proposed PQR method is shown to not only speed up the convergence of deep\nmodel training, but to also greatly improve the achievable level of quality\nprediction accuracy relative to scalar quality score regression methods. The\nsource code is available at https://github.com/HuiZeng/BIQA_Toolbox.","url_abs":"http://arxiv.org/abs/1708.08190v2","url_pdf":"http://arxiv.org/pdf/1708.08190v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-probabilistic-quality-representation","repo_url":"https://github.com/HuiZeng/BIQA_Toolbox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.08190","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}