{"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/3d-pose-estimation-for-fine-grained-object","title":"3D Pose Estimation for Fine-Grained Object Categories","arxiv_id":"1806.04314","date":"2018-06-12","proceeding":null,"authors":["Yaming Wang","Xiao Tan","Yi Yang","Xiao Liu","Errui Ding","Feng Zhou","Larry S. Davis"],"abstract":"Existing object pose estimation datasets are related to generic object types\nand there is so far no dataset for fine-grained object categories. In this\nwork, we introduce a new large dataset to benchmark pose estimation for\nfine-grained objects, thanks to the availability of both 2D and 3D fine-grained\ndata recently. Specifically, we augment two popular fine-grained recognition\ndatasets (StanfordCars and CompCars) by finding a fine-grained 3D CAD model for\neach sub-category and manually annotating each object in images with 3D pose.\nWe show that, with enough training data, a full perspective model with\ncontinuous parameters can be estimated using 2D appearance information alone.\nWe achieve this via a framework based on Faster/Mask R-CNN. This goes beyond\nprevious works on category-level pose estimation, which only estimate\ndiscrete/continuous viewpoint angles or recover rotation matrices often with\nthe help of key points. Furthermore, with fine-grained 3D models available, we\nincorporate a dense 3D representation named as location field into the\nCNN-based pose estimation framework to further improve the performance. The new\ndataset is available at www.umiacs.umd.edu/~wym/3dpose.html","url_abs":"http://arxiv.org/abs/1806.04314v3","url_pdf":"http://arxiv.org/pdf/1806.04314v3.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":"3d-pose-estimation-for-fine-grained-object","repo_url":"https://github.com/yangyi02/3d_pose_fine_grained","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"3d-pose-estimation-for-fine-grained-object","repo_url":"https://github.com/yangyi02/finegrained-pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.04314","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}