{"url":"/task/6d-pose-estimation","name":"6D Pose Estimation using RGB","slug":"6d-pose-estimation","description_markdown":"**6D Pose Estimation using RGB** refers to the task of determining the six degree-of-freedom (6D) pose of an object in 3D space based on RGB images. This involves estimating the position and orientation of an object in a scene, and is a fundamental problem in computer vision and robotics. In this task, the goal is to estimate the 6D pose of an object given an RGB image of the object and the scene, which can be used for tasks such as robotic manipulation, augmented reality, and scene reconstruction.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Segmentation-driven 6D Object Pose Estimation](https://github.com/cvlab-epfl/segmentation-driven-pose) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":233,"papers_with_code":94,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/6d-pose-estimation-on-linemod","slug":"6d-pose-estimation-on-linemod","dataset":"LineMOD","dataset_url":"/dataset/linemod-1","rows_in_archive":22,"metrics":["Mean ADD","Accuracy (ADD)","Accuracy","Mean IoU"],"first_row_in_archive_order":{"model":"RNNPose","paper_title":"RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization","paper_url":"/paper/rnnpose-recurrent-6-dof-object-pose","paper_date":"2022-03-24","arxiv_id":"2203.12870","code_links":[{"title":"decayale/rnnpose","url":"https://github.com/decayale/rnnpose"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/6d-pose-estimation-using-rgb-on-occlusion","slug":"6d-pose-estimation-using-rgb-on-occlusion","dataset":"Occlusion LineMOD","dataset_url":"/dataset/linemod-1","rows_in_archive":13,"metrics":["Mean ADD"],"first_row_in_archive_order":{"model":"SO-Pose","paper_title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","paper_url":"/paper/so-pose-exploiting-self-occlusion-for-direct","paper_date":"2021-08-18","arxiv_id":"2108.08367","code_links":[{"title":"THU-DA-6D-Pose-Group/GDR-Net","url":"https://github.com/THU-DA-6D-Pose-Group/GDR-Net"},{"title":"shangbuhuan13/so-pose","url":"https://github.com/shangbuhuan13/so-pose"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/6d-pose-estimation-on-ycb-video","slug":"6d-pose-estimation-on-ycb-video","dataset":"YCB-Video","dataset_url":"/dataset/ycb-video","rows_in_archive":5,"metrics":["Mean ADD","Accuracy (ADD)","Mean ADD-S","Mean AUC","Mean ADI"],"first_row_in_archive_order":{"model":"PoET","paper_title":"PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation","paper_url":"/paper/poet-pose-estimation-transformer-for-single","paper_date":"2022-11-25","arxiv_id":"2211.14125","code_links":[{"title":"aau-cns/poet","url":"https://github.com/aau-cns/poet"}],"syntology":null}},{"leaderboard":"/sota/6d-pose-estimation-on-occlusion","slug":"6d-pose-estimation-on-occlusion","dataset":"OCCLUSION","dataset_url":null,"rows_in_archive":2,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Single-shot deep CNN","paper_title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","paper_url":"/paper/real-time-seamless-single-shot-6d-object-pose","paper_date":"2017-11-24","arxiv_id":"1711.08848","code_links":[{"title":"Microsoft/singleshotpose","url":"https://github.com/Microsoft/singleshotpose"},{"title":"hz-ants/yolo-6d","url":"https://github.com/hz-ants/yolo-6d"},{"title":"a2824256/singleshotpose_imp","url":"https://github.com/a2824256/singleshotpose_imp"},{"title":"Yongjjun/singleshotpose","url":"https://github.com/Yongjjun/singleshotpose"},{"title":"hz-ants/obtain-an-object-mesh-and-create-labels","url":"https://github.com/hz-ants/obtain-an-object-mesh-and-create-labels"}],"syntology":null}},{"leaderboard":"/sota/6d-pose-estimation-on-t-less","slug":"6d-pose-estimation-on-t-less","dataset":"T-LESS","dataset_url":"/dataset/t-less","rows_in_archive":2,"metrics":["Recall (VSD)","Mean Recall"],"first_row_in_archive_order":{"model":"Pix2Pose without ICP","paper_title":"Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation","paper_url":"/paper/pix2pose-pixel-wise-coordinate-regression-of","paper_date":"2019-08-20","arxiv_id":"1908.07433","code_links":[{"title":"kirumang/Pix2Pose","url":"https://github.com/kirumang/Pix2Pose"},{"title":"GH3927/Pix2Pix-applied-to-cranes","url":"https://github.com/GH3927/Pix2Pix-applied-to-cranes"},{"title":"hz-ants/Pix2Pose","url":"https://github.com/hz-ants/Pix2Pose"}],"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/6d-pose-estimation-using-rgb-on-apollocar3d","slug":"6d-pose-estimation-using-rgb-on-apollocar3d","dataset":"ApolloCar3D","dataset_url":"/dataset/apollocar3d","rows_in_archive":1,"metrics":["A3DP"],"first_row_in_archive_order":{"model":"GSNet","paper_title":"GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision","paper_url":"/paper/gsnet-joint-vehicle-pose-and-shape","paper_date":"2020-07-26","arxiv_id":"2007.13124","code_links":[{"title":"lkeab/gsnet","url":"https://github.com/lkeab/gsnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/ycb-video","name":"YCB-Video","full_name":"","num_papers_in_archive":164},{"url":"/dataset/t-less","name":"T-LESS","full_name":"","num_papers_in_archive":94},{"url":"/dataset/linemod-1","name":"LM","full_name":"LINEMOD","num_papers_in_archive":34},{"url":"/dataset/apollocar3d","name":"ApolloCar3D","full_name":"","num_papers_in_archive":17},{"url":"/dataset/fraunhofer-ipa-bin-picking","name":"Fraunhofer IPA Bin-Picking","full_name":"Fraunhofer IPA Bin-Picking","num_papers_in_archive":4},{"url":"/dataset/drunkard-s-dataset","name":"Drunkard's Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/uw-indoor-scenes-uw-is-occluded-dataset","name":"UW Indoor Scenes (UW-IS) Occluded dataset","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/pose-estimation","name":"Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":94,"tagged_in_all":233,"items":[{"url":"/paper/posecnn-a-convolutional-neural-network-for-6d","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","date":"2017-11-01","arxiv_id":"1711.00199","repositories_listed":12,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/normalized-object-coordinate-space-for","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","date":"2019-01-09","arxiv_id":"1901.02970","repositories_listed":10,"syntology":{"n":20,"n_ran":4,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/estimating-6d-pose-from-localizing-designated","title":"Estimating 6D Pose From Localizing Designated Surface Keypoints","date":"2018-12-04","arxiv_id":"1812.01387","repositories_listed":6,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/bop-challenge-2020-on-6d-object-localization","title":"BOP Challenge 2020 on 6D Object Localization","date":"2020-09-15","arxiv_id":"2009.07378","repositories_listed":5,"syntology":{"n":30,"n_ran":4,"n_unverified":26,"n_pointer_only":0}},{"url":"/paper/pvnet-pixel-wise-voting-network-for-6dof-pose","title":"PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation","date":"2018-12-31","arxiv_id":"1812.11788","repositories_listed":5,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/segmentation-driven-6d-object-pose-estimation","title":"Segmentation-driven 6D Object Pose Estimation","date":"2018-12-06","arxiv_id":"1812.02541","repositories_listed":5,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/real-time-seamless-single-shot-6d-object-pose","title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","date":"2017-11-24","arxiv_id":"1711.08848","repositories_listed":5,"syntology":null},{"url":"/paper/cosypose-consistent-multi-view-multi-object","title":"CosyPose: Consistent multi-view multi-object 6D pose estimation","date":"2020-08-19","arxiv_id":"2008.08465","repositories_listed":4,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/gpv-pose-category-level-object-pose","title":"GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting","date":"2022-03-15","arxiv_id":"2203.07918","repositories_listed":3,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/efficientpose-an-efficient-accurate-and","title":"EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach","date":"2020-11-09","arxiv_id":"2011.04307","repositories_listed":3,"syntology":null},{"url":"/paper/hybridpose-6d-object-pose-estimation-under","title":"HybridPose: 6D Object Pose Estimation under Hybrid Representations","date":"2020-01-07","arxiv_id":"2001.01869","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/pix2pose-pixel-wise-coordinate-regression-of","title":"Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation","date":"2019-08-20","arxiv_id":"1908.07433","repositories_listed":3,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/pointfusion-deep-sensor-fusion-for-3d","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","date":"2017-11-29","arxiv_id":"1711.10871","repositories_listed":3,"syntology":null},{"url":"/paper/real-time-holistic-robot-pose-estimation-with","title":"Real-time Holistic Robot Pose Estimation with Unknown States","date":"2024-02-08","arxiv_id":"2402.05655","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":7}},{"url":"/paper/epro-pnp-generalized-end-to-end-probabilistic-1","title":"EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation","date":"2023-03-22","arxiv_id":"2303.12787","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":7}},{"url":"/paper/rigidity-aware-detection-for-6d-object-pose","title":"Rigidity-Aware Detection for 6D Object Pose Estimation","date":"2023-03-22","arxiv_id":"2303.12396","repositories_listed":2,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/templates-for-3d-object-pose-estimation","title":"Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions","date":"2022-03-31","arxiv_id":"2203.17234","repositories_listed":2,"syntology":null},{"url":"/paper/roft-real-time-optical-flow-aided-6d-object","title":"ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking","date":"2021-11-06","arxiv_id":"2111.03821","repositories_listed":2,"syntology":null},{"url":"/paper/so-pose-exploiting-self-occlusion-for-direct","title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","date":"2021-08-18","arxiv_id":"2108.08367","repositories_listed":2,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/dexycb-a-benchmark-for-capturing-hand","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","date":"2021-04-09","arxiv_id":"2104.04631","repositories_listed":2,"syntology":null},{"url":"/paper/wide-depth-range-6d-object-pose-estimation-in","title":"Wide-Depth-Range 6D Object Pose Estimation in Space","date":"2021-04-01","arxiv_id":"2104.00337","repositories_listed":2,"syntology":null},{"url":"/paper/fs-net-fast-shape-based-network-for-category","title":"FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism","date":"2021-03-12","arxiv_id":"2103.07054","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/gdr-net-geometry-guided-direct-regression","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","date":"2021-02-24","arxiv_id":"2102.12145","repositories_listed":2,"syntology":null},{"url":"/paper/bpnp-further-empowering-end-to-end-learning","title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization","date":"2019-09-13","arxiv_id":"1909.06043","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/dpod-dense-6d-pose-object-detector-in-rgb","title":"DPOD: 6D Pose Object Detector and Refiner","date":"2019-02-28","arxiv_id":"1902.11020","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/silhonet-an-rgb-method-for-6d-object-pose","title":"SilhoNet: An RGB Method for 6D Object Pose Estimation","date":"2018-09-18","arxiv_id":"1809.06893","repositories_listed":2,"syntology":null},{"url":"/paper/deepim-deep-iterative-matching-for-6d-pose","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","date":"2018-03-31","arxiv_id":"1804.00175","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/bb8-a-scalable-accurate-robust-to-partial","title":"BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth","date":"2017-03-31","arxiv_id":"1703.10896","repositories_listed":2,"syntology":null},{"url":"/paper/t-less-an-rgb-d-dataset-for-6d-pose","title":"T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects","date":"2017-01-19","arxiv_id":"1701.05498","repositories_listed":2,"syntology":null},{"url":"/paper/senseshift6d-multimodal-rgb-d-benchmarking","title":"SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations","date":"2025-07-08","arxiv_id":"2507.05751","repositories_listed":1,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}