{"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/morphological-networks-for-image-de-raining","title":"Morphological Networks for Image De-raining","arxiv_id":"1901.02411","date":"2019-01-08","proceeding":null,"authors":["Ranjan Mondal","Pulak Purkait","Sanchayan Santra","Bhabatosh Chanda"],"abstract":"Mathematical morphological methods have successfully been applied to filter\nout (emphasize or remove) different structures of an image. However, it is\nargued that these methods could be suitable for the task only if the type and\norder of the filter(s) as well as the shape and size of operator kernel are\ndesigned properly. Thus the existing filtering operators are problem (instance)\nspecific and are designed by the domain experts. In this work we propose a\nmorphological network that emulates classical morphological filtering\nconsisting of a series of erosion and dilation operators with trainable\nstructuring elements. We evaluate the proposed network for image de-raining\ntask where the SSIM and mean absolute error (MAE) loss corresponding to\npredicted and ground-truth clean image is back-propagated through the network\nto train the structuring elements. We observe that a single morphological\nnetwork can de-rain an image with any arbitrary shaped rain-droplets and\nachieves similar performance with the contemporary CNNs for this task with a\nfraction of trainable parameters (network size). The proposed morphological\nnetwork(MorphoN) is not designed specifically for de-raining and can readily be\napplied to similar filtering / noise cleaning tasks. The source code can be\nfound here https://github.com/ranjanZ/2D-Morphological-Network","url_abs":"http://arxiv.org/abs/1901.02411v1","url_pdf":"http://arxiv.org/pdf/1901.02411v1.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":"morphological-networks-for-image-de-raining","repo_url":"https://github.com/ranjanZ/2D-Morphological-Network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"ssim","task_name":"SSIM"}],"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}