{"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/burst-ranking-for-blind-multi-image","title":"Burst ranking for blind multi-image deblurring","arxiv_id":"1810.12121","date":"2018-10-29","proceeding":null,"authors":["Fidel A. Guerrero Peña","Pedro D. Marrero Fernández","Tsang Ing Ren","Jorge J. G. Leandro","Ricardo Nishihara"],"abstract":"We propose a new incremental aggregation algorithm for multi-image deblurring\nwith automatic image selection. The primary motivation is that current bursts\ndeblurring methods do not handle well situations in which misalignment or\nout-of-context frames are present in the burst. These real-life situations\nresult in poor reconstructions or manual selection of the images that will be\nused to deblur. Automatically selecting best frames within the burst to improve\nthe base reconstruction is challenging because the amount of possible images\nfusions is equal to the power set cardinal. Here, we approach the multi-image\ndeblurring problem as a two steps process. First, we successfully learn a\ncomparison function to rank a burst of images using a deep convolutional neural\nnetwork. Then, an incremental Fourier burst accumulation with a reconstruction\ndegradation mechanism is applied fusing only less blurred images that are\nsufficient to maximize the reconstruction quality. Experiments with the\nproposed algorithm have shown superior results when compared to other similar\napproaches, outperforming other methods described in the literature in\npreviously described situations. We validate our findings on several synthetic\nand real datasets.","url_abs":"http://arxiv.org/abs/1810.12121v2","url_pdf":"http://arxiv.org/pdf/1810.12121v2.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":"burst-ranking-for-blind-multi-image","repo_url":"https://github.com/HelenGuohx/cv-ferattn-code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"burst-ranking-for-blind-multi-image","repo_url":"https://github.com/pedrodiamel/ferattention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}