{"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/efficient-misalignment-robust-multi-focus","title":"Efficient Misalignment-Robust Multi-Focus Microscopical Images Fusion","arxiv_id":"1812.08915","date":"2018-12-21","proceeding":null,"authors":["Yixiong Liang","Yuan Mao","Zhihong Tang","Meng Yan","Yuqian Zhao","Jianfeng Liu"],"abstract":"In this paper we propose a very efficient method to fuse the unregistered\nmulti-focus microscopical images based on the speed-up robust features (SURF).\nOur method follows the pipeline of first registration and then fusion. However,\ninstead of treating the registration and fusion as two completely independent\nstage, we propose to reuse the determinant of the approximate Hessian generated\nin SURF detection stage as the corresponding salient response for the final\nimage fusion, thus it enables nearly cost-free saliency map generation. In\naddition, due to the adoption of SURF scale space representation, our method\ncan generate scale-invariant saliency map which is desired for scale-invariant\nimage fusion. We present an extensive evaluation on the dataset consisting of\nseveral groups of unregistered multi-focus 4K ultra HD microscopic images with\nsize of 4112 x 3008. Compared with the state-of-the-art multi-focus image\nfusion methods, our method is much faster and achieve better results in the\nvisual performance. Our method provides a flexible and efficient way to\nintegrate complementary and redundant information from multiple multi-focus\nultra HD unregistered images into a fused image that contains better\ndescription than any of the individual input images. Code is available at\nhttps://github.com/yiqingmy/JointRF.","url_abs":"http://arxiv.org/abs/1812.08915v1","url_pdf":"http://arxiv.org/pdf/1812.08915v1.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":"efficient-misalignment-robust-multi-focus","repo_url":"https://github.com/yiqingmy/JointRF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"multi-focus-image-fusion","task_name":"Multi Focus Image Fusion"},{"task_slug":"multi-focus-microscopical-images-fusion","task_name":"Multi-Focus Microscopical Images Fusion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}