{"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/implicit-3d-orientation-learning-for-6d","title":"Implicit 3D Orientation Learning for 6D Object Detection from RGB Images","arxiv_id":"1902.01275","date":"2019-02-04","proceeding":"ECCV 2018 9","authors":["Martin Sundermeyer","Zoltan-Csaba Marton","Maximilian Durner","Manuel Brucker","Rudolph Triebel"],"abstract":"We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization. This so-called Augmented Autoencoder has several advantages over existing methods: It does not require real, pose-annotated training data, generalizes to various test sensors and inherently handles object and view symmetries. Instead of learning an explicit mapping from input images to object poses, it provides an implicit representation of object orientations defined by samples in a latent space. Our pipeline achieves state-of-the-art performance on the T-LESS dataset both in the RGB and RGB-D domain. We also evaluate on the LineMOD dataset where we can compete with other synthetically trained approaches. We further increase performance by correcting 3D orientation estimates to account for perspective errors when the object deviates from the image center and show extended results.","url_abs":"https://arxiv.org/abs/1902.01275v2","url_pdf":"https://arxiv.org/pdf/1902.01275v2.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":"implicit-3d-orientation-learning-for-6d","repo_url":"https://github.com/DLR-RM/AugmentedAutoencoder","is_official":1,"mentioned_in_paper":1,"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":"denoising","task_name":"Denoising"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-on-linemod","task":"6D Pose Estimation using RGB","dataset":"LineMOD","model":"Augmented Autoencoder","rank_in_archive_order":21,"of":22,"metrics":{"Mean ADD":"28.7"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-on-t-less","task":"6D Pose Estimation using RGB","dataset":"T-LESS","model":"Augmented Autoencoder","rank_in_archive_order":2,"of":2,"metrics":{"Mean Recall":"36.8"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-using-rgbd-on-linemod","task":"6D Pose Estimation using RGBD","dataset":"LineMOD","model":"Augmented Autoencoder","rank_in_archive_order":7,"of":8,"metrics":{"Mean ADD":"64.67"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-using-rgbd-on-t-less","task":"6D Pose Estimation using RGBD","dataset":"T-LESS","model":"Augmented Autoencoder","rank_in_archive_order":1,"of":1,"metrics":{"Mean Recall":"72.76"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.01275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01275"}},"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/DLR-RM/AugmentedAutoencoder","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"ca023a517e3f75c9","entry":"build_dataset","repo":"DLR-RM/AugmentedAutoencoder","repo_kind":"official","path":"auto_pose/ae/ae_factory.py","file_url":"https://github.com/DLR-RM/AugmentedAutoencoder/blob/HEAD/auto_pose/ae/ae_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca023a517e3f75c9"}},{"code_sha256_prefix":"2312a44de750ce76","entry":"build_encoder","repo":"DLR-RM/AugmentedAutoencoder","repo_kind":"official","path":"auto_pose/ae/ae_factory.py","file_url":"https://github.com/DLR-RM/AugmentedAutoencoder/blob/HEAD/auto_pose/ae/ae_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2312a44de750ce76"}},{"code_sha256_prefix":"0ef213a7e7f2452b","entry":"build_queue","repo":"DLR-RM/AugmentedAutoencoder","repo_kind":"official","path":"auto_pose/ae/ae_factory.py","file_url":"https://github.com/DLR-RM/AugmentedAutoencoder/blob/HEAD/auto_pose/ae/ae_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ef213a7e7f2452b"}},{"code_sha256_prefix":"88d0e71863a71fc7","entry":"calc_recall","repo":"DLR-RM/AugmentedAutoencoder","repo_kind":"official","path":"sixd_toolkit_extensions/eval_loc.py","file_url":"https://github.com/DLR-RM/AugmentedAutoencoder/blob/HEAD/sixd_toolkit_extensions/eval_loc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88d0e71863a71fc7"}},{"code_sha256_prefix":"6c60ed298bb23701","entry":"calc_scores","repo":"DLR-RM/AugmentedAutoencoder","repo_kind":"official","path":"sixd_toolkit_extensions/eval_loc.py","file_url":"https://github.com/DLR-RM/AugmentedAutoencoder/blob/HEAD/sixd_toolkit_extensions/eval_loc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c60ed298bb23701"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}