{"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/structured-uncertainty-prediction-networks","title":"Structured Uncertainty Prediction Networks","arxiv_id":"1802.07079","date":"2018-02-20","proceeding":"CVPR 2018 6","authors":["Garoe Dorta","Sara Vicente","Lourdes Agapito","Neill D. F. Campbell","Ivor Simpson"],"abstract":"This paper is the first work to propose a network to predict a structured\nuncertainty distribution for a synthesized image. Previous approaches have been\nmostly limited to predicting diagonal covariance matrices. Our novel model\nlearns to predict a full Gaussian covariance matrix for each reconstruction,\nwhich permits efficient sampling and likelihood evaluation.\n  We demonstrate that our model can accurately reconstruct ground truth\ncorrelated residual distributions for synthetic datasets and generate plausible\nhigh frequency samples for real face images. We also illustrate the use of\nthese predicted covariances for structure preserving image denoising.","url_abs":"http://arxiv.org/abs/1802.07079v2","url_pdf":"http://arxiv.org/pdf/1802.07079v2.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":"structured-uncertainty-prediction-networks","repo_url":"https://github.com/Garoe/tf_mvg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"structured-uncertainty-prediction-networks","repo_url":"https://github.com/era-dorta/tf_mvg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1802.07079","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}