{"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/improving-electron-micrograph-signal-to-noise","title":"Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder","arxiv_id":"1807.11234","date":"2018-07-30","proceeding":null,"authors":["Jeffrey M. Ede"],"abstract":"We present an atrous convolutional encoder-decoder trained to denoise\n512$\\times$512 crops from electron micrographs. It consists of a modified\nXception backbone, atrous convoltional spatial pyramid pooling module and a\nmulti-stage decoder. Our neural network was trained end-to-end to remove\nPoisson noise applied to low-dose ($\\ll$ 300 counts ppx) micrographs created\nfrom a new dataset of 17267 2048$\\times$2048 high-dose ($>$ 2500 counts ppx)\nmicrographs and then fine-tuned for ordinary doses (200-2500 counts ppx). Its\nperformance is benchmarked against bilateral, non-local means, total variation,\nwavelet, Wiener and other restoration methods with their default parameters.\nOur network outperforms their best mean squared error and structural similarity\nindex performances by 24.6% and 9.6% for low doses and by 43.7% and 5.5% for\nordinary doses. In both cases, our network's mean squared error has the lowest\nvariance. Source code and links to our new high-quality dataset and trained\nnetwork have been made publicly available at\nhttps://github.com/Jeffrey-Ede/Electron-Micrograph-Denoiser","url_abs":"http://arxiv.org/abs/1807.11234v2","url_pdf":"http://arxiv.org/pdf/1807.11234v2.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":"improving-electron-micrograph-signal-to-noise","repo_url":"https://github.com/Jeffrey-Ede/Electron-Micrograph-Denoiser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"2048","task_name":"Playing the Game of 2048"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}