{"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/a-review-of-convolutional-neural-networks-for","title":"A Review of Convolutional Neural Networks for Inverse Problems in Imaging","arxiv_id":"1710.04011","date":"2017-10-11","proceeding":null,"authors":["Michael T. McCann","Kyong Hwan Jin","Michael Unser"],"abstract":"In this survey paper, we review recent uses of convolution neural networks\n(CNNs) to solve inverse problems in imaging. It has recently become feasible to\ntrain deep CNNs on large databases of images, and they have shown outstanding\nperformance on object classification and segmentation tasks. Motivated by these\nsuccesses, researchers have begun to apply CNNs to the resolution of inverse\nproblems such as denoising, deconvolution, super-resolution, and medical image\nreconstruction, and they have started to report improvements over\nstate-of-the-art methods, including sparsity-based techniques such as\ncompressed sensing. Here, we review the recent experimental work in these\nareas, with a focus on the critical design decisions: Where does the training\ndata come from? What is the architecture of the CNN? and How is the learning\nproblem formulated and solved? We also bring together a few key theoretical\npapers that offer perspective on why CNNs are appropriate for inverse problems\nand point to some next steps in the field.","url_abs":"http://arxiv.org/abs/1710.04011v1","url_pdf":"http://arxiv.org/pdf/1710.04011v1.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":"a-review-of-convolutional-neural-networks-for","repo_url":"https://github.com/IMAC-projects/Deblurring-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-review-of-convolutional-neural-networks-for","repo_url":"https://github.com/IMAC-projects/SRN-Deblurring-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.04011","atlas_url":"https://app.syntology.ai/?focus=1710.04011","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}