{"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/tangent-images-for-mitigating-spherical","title":"Tangent Images for Mitigating Spherical Distortion","arxiv_id":"1912.09390","date":"2019-12-19","proceeding":"CVPR 2020 6","authors":["Marc Eder","Mykhailo Shvets","John Lim","Jan-Michael Frahm"],"abstract":"In this work, we propose \"tangent images,\" a spherical image representation that facilitates transferable and scalable $360^\\circ$ computer vision. Inspired by techniques in cartography and computer graphics, we render a spherical image to a set of distortion-mitigated, locally-planar image grids tangent to a subdivided icosahedron. By varying the resolution of these grids independently of the subdivision level, we can effectively represent high resolution spherical images while still benefiting from the low-distortion icosahedral spherical approximation. We show that training standard convolutional neural networks on tangent images compares favorably to the many specialized spherical convolutional kernels that have been developed, while also scaling efficiently to handle significantly higher spherical resolutions. Furthermore, because our approach does not require specialized kernels, we show that we can transfer networks trained on perspective images to spherical data without fine-tuning and with limited performance drop-off. Finally, we demonstrate that tangent images can be used to improve the quality of sparse feature detection on spherical images, illustrating its usefulness for traditional computer vision tasks like structure-from-motion and SLAM.","url_abs":"https://arxiv.org/abs/1912.09390v3","url_pdf":"https://arxiv.org/pdf/1912.09390v3.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":"tangent-images-for-mitigating-spherical","repo_url":"https://github.com/meder411/Tangent-Images","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"Tangent (ResNet-101)","rank_in_archive_order":19,"of":25,"metrics":{"mAcc":"65.2","mIoU":"45.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-2","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic - RGBD","model":"Tangent (ResNet-101)","rank_in_archive_order":2,"of":3,"metrics":{"mAcc":"69.1","mIoU":"51.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1912.09390","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}