{"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/ntop-nerf-powered-large-scale-dataset","title":"NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images","arxiv_id":"2402.18196","date":"2024-02-28","proceeding":null,"authors":["Jingrui Yu","Dipankar Nandi","Roman Seidel","Gangolf Hirtz"],"abstract":"Human pose estimation (HPE) in the top-view using fisheye cameras presents a promising and innovative application domain. However, the availability of datasets capturing this viewpoint is extremely limited, especially those with high-quality 2D and 3D keypoint annotations. Addressing this gap, we leverage the capabilities of Neural Radiance Fields (NeRF) technique to establish a comprehensive pipeline for generating human pose datasets from existing 2D and 3D datasets, specifically tailored for the top-view fisheye perspective. Through this pipeline, we create a novel dataset NToP570K (NeRF-powered Top-view human Pose dataset for fisheye cameras with over 570 thousand images), and conduct an extensive evaluation of its efficacy in enhancing neural networks for 2D and 3D top-view human pose estimation. A pretrained ViTPose-B model achieves an improvement in AP of 33.3 % on our validation set for 2D HPE after finetuning on our training set. A similarly finetuned HybrIK-Transformer model gains 53.7 mm reduction in PA-MPJPE for 3D HPE on the validation set.","url_abs":"https://arxiv.org/abs/2402.18196v2","url_pdf":"https://arxiv.org/pdf/2402.18196v2.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":"ntop-nerf-powered-large-scale-dataset","repo_url":"https://github.com/yu-jingrui/NToP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"dataset-generation","task_name":"Dataset Generation"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[{"slug":"ntop","name":"NToP","full_name":""},{"slug":"omnilab","name":"OmniLab","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}