{"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-haar-wavelet-based-perceptual-similarity","title":"A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment","arxiv_id":"1607.06140","date":"2016-07-20","proceeding":null,"authors":["Rafael Reisenhofer","Sebastian Bosse","Gitta Kutyniok","Thomas Wiegand"],"abstract":"In most practical situations, the compression or transmission of images and\nvideos creates distortions that will eventually be perceived by a human\nobserver. Vice versa, image and video restoration techniques, such as\ninpainting or denoising, aim to enhance the quality of experience of human\nviewers. Correctly assessing the similarity between an image and an undistorted\nreference image as subjectively experienced by a human viewer can thus lead to\nsignificant improvements in any transmission, compression, or restoration\nsystem. This paper introduces the Haar wavelet-based perceptual similarity\nindex (HaarPSI), a novel and computationally inexpensive similarity measure for\nfull reference image quality assessment. The HaarPSI utilizes the coefficients\nobtained from a Haar wavelet decomposition to assess local similarities between\ntwo images, as well as the relative importance of image areas. The consistency\nof the HaarPSI with the human quality of experience was validated on four large\nbenchmark databases containing thousands of differently distorted images. On\nthese databases, the HaarPSI achieves higher correlations with human opinion\nscores than state-of-the-art full reference similarity measures like the\nstructural similarity index (SSIM), the feature similarity index (FSIM), and\nthe visual saliency-based index (VSI). Along with the simple computational\nstructure and the short execution time, these experimental results suggest a\nhigh applicability of the HaarPSI in real world tasks.","url_abs":"http://arxiv.org/abs/1607.06140v4","url_pdf":"http://arxiv.org/pdf/1607.06140v4.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":[],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"full-reference-image-quality-assessment","task_name":"Full reference image quality assessment"},{"task_slug":"full-reference-image-quality-assessment-2","task_name":"Full-Reference Image Quality Assessment"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"video-restoration","task_name":"Video Restoration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/full-reference-image-quality-assessment-on-3","task":"Full reference image quality assessment","dataset":"ESPL","model":"HaarPSI","rank_in_archive_order":6,"of":11,"metrics":{"PLCC":"0.8526","SRCC":"0.8510"},"uses_additional_data":false},{"leaderboard":"/sota/full-reference-image-quality-assessment-on-2","task":"Full reference image quality assessment","dataset":"KADID10K","model":"HaarPSI","rank_in_archive_order":2,"of":11,"metrics":{"SRCC":"0.8849"},"uses_additional_data":false},{"leaderboard":"/sota/full-reference-image-quality-assessment-on","task":"Full reference image quality assessment","dataset":"TID2008","model":"HaarPSI","rank_in_archive_order":2,"of":13,"metrics":{"PLCC":"0.9074","SRCC":"0.9104"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-video-quality-1","task":"Video Quality Assessment","dataset":"MSU FR VQA Database","model":"HaarPSI","rank_in_archive_order":12,"of":20,"metrics":{"KLCC":"0.7451","SRCC":"0.8982"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.06140","atlas_url":"https://app.syntology.ai/?focus=1607.06140","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}