{"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/fsd-fast-self-supervised-single-rgb-d-to","title":"FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects","arxiv_id":"2310.12974","date":"2023-10-19","proceeding":null,"authors":["Mayank Lunayach","Sergey Zakharov","Dian Chen","Rares Ambrus","Zsolt Kira","Muhammad Zubair Irshad"],"abstract":"In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data. Our goal is to predict the 3D shape, size, and 6D pose of objects within a single RGB-D image, operating at the category level and eliminating the need for CAD models during inference. While existing self-supervised methods have made strides in this field, they often suffer from inefficiencies arising from non-end-to-end processing, reliance on separate models for different object categories, and slow surface extraction during the training of implicit reconstruction models; thus hindering both the speed and real-world applicability of the 3D recognition process. Our proposed method leverages a multi-stage training pipeline, designed to efficiently transfer synthetic performance to the real-world domain. This approach is achieved through a combination of 2D and 3D supervised losses during the synthetic domain training, followed by the incorporation of 2D supervised and 3D self-supervised losses on real-world data in two additional learning stages. By adopting this comprehensive strategy, our method successfully overcomes the aforementioned limitations and outperforms existing self-supervised 6D pose and size estimation baselines on the NOCS test-set with a 16.4% absolute improvement in mAP for 6D pose estimation while running in near real-time at 5 Hz.","url_abs":"https://arxiv.org/abs/2310.12974v1","url_pdf":"https://arxiv.org/pdf/2310.12974v1.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":"fsd-fast-self-supervised-single-rgb-d-to","repo_url":"https://github.com/zubair-irshad/shapo","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-object-recognition","task_name":"3D Object Recognition"},{"task_slug":"6d-pose-estimation-1","task_name":"6D Pose Estimation"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.12974","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}