{"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/gvnn-neural-network-library-for-geometric","title":"gvnn: Neural Network Library for Geometric Computer Vision","arxiv_id":"1607.07405","date":"2016-07-25","proceeding":null,"authors":["Ankur Handa","Michael Bloesch","Viorica Patraucean","Simon Stent","John McCormac","Andrew Davison"],"abstract":"We introduce gvnn, a neural network library in Torch aimed towards bridging\nthe gap between classic geometric computer vision and deep learning. Inspired\nby the recent success of Spatial Transformer Networks, we propose several new\nlayers which are often used as parametric transformations on the data in\ngeometric computer vision. These layers can be inserted within a neural network\nmuch in the spirit of the original spatial transformers and allow\nbackpropagation to enable end-to-end learning of a network involving any domain\nknowledge in geometric computer vision. This opens up applications in learning\ninvariance to 3D geometric transformation for place recognition, end-to-end\nvisual odometry, depth estimation and unsupervised learning through warping\nwith a parametric transformation for image reconstruction error.","url_abs":"http://arxiv.org/abs/1607.07405v3","url_pdf":"http://arxiv.org/pdf/1607.07405v3.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":"gvnn-neural-network-library-for-geometric","repo_url":"https://github.com/ankurhanda/gvnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"visual-odometry","task_name":"Visual Odometry"}],"methods":[{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1607.07405","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}