{"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/synthesizing-filamentary-structured-images","title":"Synthesizing Filamentary Structured Images with GANs","arxiv_id":"1706.02185","date":"2017-06-07","proceeding":null,"authors":["He Zhao","Huiqi Li","Li Cheng"],"abstract":"This paper aims at synthesizing filamentary structured images such as retinal\nfundus images and neuronal images, as follows: Given a ground-truth, to\ngenerate multiple realistic looking phantoms. A ground-truth could be a binary\nsegmentation map containing the filamentary structured morphology, while the\nsynthesized output image is of the same size as the ground-truth and has\nsimilar visual appearance to what have been presented in the training set. Our\napproach is inspired by the recent progresses in generative adversarial nets\n(GANs) as well as image style transfer. In particular, it is dedicated to our\nproblem context with the following properties: Rather than large-scale dataset,\nit works well in the presence of as few as 10 training examples, which is\ncommon in medical image analysis; It is capable of synthesizing diverse images\nfrom the same ground-truth; Last and importantly, the synthetic images produced\nby our approach are demonstrated to be useful in boosting image analysis\nperformance. Empirical examination over various benchmarks of fundus and\nneuronal images demonstrate the advantages of the proposed approach.","url_abs":"http://arxiv.org/abs/1706.02185v1","url_pdf":"http://arxiv.org/pdf/1706.02185v1.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":"synthesizing-filamentary-structured-images","repo_url":"https://github.com/ibrahimayaz/Fila-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"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}