{"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/posecnn-a-convolutional-neural-network-for-6d","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","arxiv_id":"1711.00199","date":"2017-11-01","proceeding":null,"authors":["Yu Xiang","Tanner Schmidt","Venkatraman Narayanan","Dieter Fox"],"abstract":"Estimating the 6D pose of known objects is important for robots to interact\nwith the real world. The problem is challenging due to the variety of objects\nas well as the complexity of a scene caused by clutter and occlusions between\nobjects. In this work, we introduce PoseCNN, a new Convolutional Neural Network\nfor 6D object pose estimation. PoseCNN estimates the 3D translation of an\nobject by localizing its center in the image and predicting its distance from\nthe camera. The 3D rotation of the object is estimated by regressing to a\nquaternion representation. We also introduce a novel loss function that enables\nPoseCNN to handle symmetric objects. In addition, we contribute a large scale\nvideo dataset for 6D object pose estimation named the YCB-Video dataset. Our\ndataset provides accurate 6D poses of 21 objects from the YCB dataset observed\nin 92 videos with 133,827 frames. We conduct extensive experiments on our\nYCB-Video dataset and the OccludedLINEMOD dataset to show that PoseCNN is\nhighly robust to occlusions, can handle symmetric objects, and provide accurate\npose estimation using only color images as input. When using depth data to\nfurther refine the poses, our approach achieves state-of-the-art results on the\nchallenging OccludedLINEMOD dataset. Our code and dataset are available at\nhttps://rse-lab.cs.washington.edu/projects/posecnn/.","url_abs":"http://arxiv.org/abs/1711.00199v3","url_pdf":"http://arxiv.org/pdf/1711.00199v3.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":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/NVlabs/PoseCNN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/RiplleYang/DenseFusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/Theopetitjean/DenseFusion_R_Invariant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/Yotonctu/densefusion_torch1.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/caoquan95/6D-pose-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/cxt98/Densefusion-transparency","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/hz-ants/DenseFusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/hz-ants/Posecnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/leob03/E2E_Object_Pose_Estimator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/varunburde/reconstruction_pose_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/verityw/manipulation-final-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"posecnn-a-convolutional-neural-network-for-6d","repo_url":"https://github.com/yuxng/PoseCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"6d-pose-estimation-1","task_name":"6D Pose Estimation"},{"task_slug":"6d-pose-estimation","task_name":"6D Pose Estimation using RGB"},{"task_slug":"6d-pose-estimation-using-rgbd","task_name":"6D Pose Estimation using RGBD"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"ycb-video","name":"YCB-Video","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-on-ycb-video-2","task":"6D Pose Estimation","dataset":"YCB-Video","model":"PoseCNN+ICP","rank_in_archive_order":10,"of":10,"metrics":{"ADDS AUC":"93.0"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-on-ycb-video","task":"6D Pose Estimation using RGB","dataset":"YCB-Video","model":"PoseCNN","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy (ADD)":"21.3%","Mean ADD":"53.7","Mean ADD-S":"75.9"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-using-rgbd-on-ycb-video","task":"6D Pose Estimation using RGBD","dataset":"YCB-Video","model":"PoseCNN (ICP)","rank_in_archive_order":4,"of":9,"metrics":{"Mean ADD":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-using-rgbd-on-ycb-video","task":"6D Pose Estimation using RGBD","dataset":"YCB-Video","model":"ALL PoseCNN+ICP","rank_in_archive_order":6,"of":9,"metrics":{"Mean ADD-S":"93"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.00199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00199"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NVlabs/PoseCNN-PyTorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cxt98/Densefusion-transparency","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Yotonctu/densefusion_torch1.0","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/verityw/manipulation-final-project","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leob03/E2E_Object_Pose_Estimator","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hz-ants/Posecnn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Theopetitjean/DenseFusion_R_Invariant","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuxng/PoseCNN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RiplleYang/DenseFusion","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/caoquan95/6D-pose-project","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hz-ants/DenseFusion","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/varunburde/reconstruction_pose_benchmark","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"ccaa56ff47071ce3","entry":"eval","repo":"leob03/E2E_Object_Pose_Estimator","repo_kind":"listed","path":"pose_cnn.py","file_url":"https://github.com/leob03/E2E_Object_Pose_Estimator/blob/HEAD/pose_cnn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccaa56ff47071ce3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}