{"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/gps-glass-learning-nighttime-semantic","title":"GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data","arxiv_id":"2207.13297","date":"2022-07-27","proceeding":null,"authors":["Hongjae Lee","Changwoo Han","Jun-Sang Yoo","Seung-Won Jung"],"abstract":"Semantic segmentation for autonomous driving should be robust against various in-the-wild environments. Nighttime semantic segmentation is especially challenging due to a lack of annotated nighttime images and a large domain gap from daytime images with sufficient annotation. In this paper, we propose a novel GPS-based training framework for nighttime semantic segmentation. Given GPS-aligned pairs of daytime and nighttime images, we perform cross-domain correspondence matching to obtain pixel-level pseudo supervision. Moreover, we conduct flow estimation between daytime video frames and apply GPS-based scaling to acquire another pixel-level pseudo supervision. Using these pseudo supervisions with a confidence map, we train a nighttime semantic segmentation network without any annotation from nighttime images. Experimental results demonstrate the effectiveness of the proposed method on several nighttime semantic segmentation datasets. Our source code is available at https://github.com/jimmy9704/GPS-GLASS.","url_abs":"https://arxiv.org/abs/2207.13297v5","url_pdf":"https://arxiv.org/pdf/2207.13297v5.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":"gps-glass-learning-nighttime-semantic","repo_url":"https://github.com/jimmy9704/gps-glass","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"dense-pixel-correspondence-estimation","task_name":"Dense Pixel Correspondence Estimation"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-dark-zurich","task":"Semantic Segmentation","dataset":"Dark Zurich","model":"GPS-GLASS","rank_in_archive_order":8,"of":14,"metrics":{"mIoU":"46.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2207.13297","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}