{"url":"/sota/6d-pose-estimation-using-rgb-on-occlusion","task":{"name":"6D Pose Estimation using RGB","url":"/task/6d-pose-estimation","note":null},"dataset":{"name":"Occlusion LineMOD","url":"/dataset/linemod-1"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**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>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Mean ADD"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean ADD":null}},"counts":{"rows":13,"rows_with_code":11,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SO-Pose","metrics":{"Mean ADD":"62.3"},"uses_additional_data":false,"paper_date":"2021-08-18","paper":"/paper/so-pose-exploiting-self-occlusion-for-direct","paper_url":"https://arxiv.org/abs/2108.08367v1","paper_title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","code":"https://github.com/THU-DA-6D-Pose-Group/GDR-Net","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":16,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"RNNPose (Trained with synthetic data and LINEMOD training set, w/o pbr data)","metrics":{"Mean ADD":"60.65"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/rnnpose-recurrent-6-dof-object-pose","paper_url":"https://arxiv.org/abs/2203.12870v3","paper_title":"RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization","code":"https://github.com/decayale/rnnpose","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"GDR-Net","metrics":{"Mean ADD":"56.1"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/gdr-net-geometry-guided-direct-regression","paper_url":"https://arxiv.org/abs/2102.12145v5","paper_title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","code":"https://github.com/THU-DA-6D-Pose-Group/GDR-Net","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"DeepIM (Train on Occlusion LineMOD)","metrics":{"Mean ADD":"55.5"},"uses_additional_data":false,"paper_date":"2018-03-31","paper":"/paper/deepim-deep-iterative-matching-for-6d-pose","paper_url":"https://arxiv.org/abs/1804.00175v4","paper_title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","code":"https://github.com/liyi14/mx-DeepIM","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"PPC (Refined from initial PVNet pose)","metrics":{"Mean ADD":"55.33"},"uses_additional_data":false,"paper_date":"2020-05-13","paper":"/paper/pose-proposal-critic-robust-pose-refinement","paper_url":"https://arxiv.org/abs/2005.06262v2","paper_title":"Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"RePOSE","metrics":{"Mean ADD":"51.6"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/repose-real-time-iterative-rendering-and","paper_url":"https://arxiv.org/abs/2104.00633v2","paper_title":"RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering","code":"https://github.com/sh8/repose","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"HybridPose","metrics":{"Mean ADD":"47.5"},"uses_additional_data":false,"paper_date":"2020-01-07","paper":"/paper/hybridpose-6d-object-pose-estimation-under","paper_url":"https://arxiv.org/abs/2001.01869v4","paper_title":"HybridPose: 6D Object Pose Estimation under Hybrid Representations","code":"https://github.com/chensong1995/HybridPose","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":8,"model":"E2E6DoF","metrics":{"Mean ADD":"47.4"},"uses_additional_data":false,"paper_date":"2020-11-22","paper":"/paper/end-to-end-differentiable-6dof-object-pose","paper_url":"https://arxiv.org/abs/2011.11078v1","paper_title":"End-to-End Differentiable 6DoF Object Pose Estimation with Local and Global Constraints","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"DPOD","metrics":{"Mean ADD":"47.25"},"uses_additional_data":false,"paper_date":"2019-02-28","paper":"/paper/dpod-dense-6d-pose-object-detector-in-rgb","paper_url":"https://arxiv.org/abs/1902.11020v3","paper_title":"DPOD: 6D Pose Object Detector and Refiner","code":"https://github.com/yshah43/DPOD","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"ROPE","metrics":{"Mean ADD":"45.95"},"uses_additional_data":false,"paper_date":"2021-10-22","paper":"/paper/occlusion-robust-object-pose-estimation-with","paper_url":"https://arxiv.org/abs/2110.11636v1","paper_title":"Occlusion-Robust Object Pose Estimation with Holistic Representation","code":"https://github.com/bochenys/rope","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"PVNet","metrics":{"Mean ADD":"40.77"},"uses_additional_data":false,"paper_date":"2018-12-31","paper":"/paper/pvnet-pixel-wise-voting-network-for-6dof-pose","paper_url":"http://arxiv.org/abs/1812.11788v1","paper_title":"PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation","code":"https://github.com/zju3dv/pvnet","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"SegDriven","metrics":{"Mean ADD":"27"},"uses_additional_data":false,"paper_date":"2018-12-06","paper":"/paper/segmentation-driven-6d-object-pose-estimation","paper_url":"http://arxiv.org/abs/1812.02541v3","paper_title":"Segmentation-driven 6D Object Pose Estimation","code":"https://github.com/cvlab-epfl/segmentation-driven-pose","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"CullNet","metrics":{"Mean ADD":"24.48"},"uses_additional_data":false,"paper_date":"2019-09-30","paper":"/paper/cullnet-calibrated-and-pose-aware-confidence","paper_url":"https://arxiv.org/abs/1909.13476v1","paper_title":"CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation","code":"https://github.com/kartikgupta-at-anu/CullNet","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":8,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":57,"n_samples":65,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":57,"n_samples":65,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}