{"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/deepim-deep-iterative-matching-for-6d-pose","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","arxiv_id":"1804.00175","date":"2018-03-31","proceeding":"ECCV 2018 9","authors":["Yi Li","Gu Wang","Xiangyang Ji","Yu Xiang","Dieter Fox"],"abstract":"Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the observed image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using an untangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over state-of-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.","url_abs":"https://arxiv.org/abs/1804.00175v4","url_pdf":"https://arxiv.org/pdf/1804.00175v4.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":"deepim-deep-iterative-matching-for-6d-pose","repo_url":"https://github.com/liyi14/mx-DeepIM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deepim-deep-iterative-matching-for-6d-pose","repo_url":"https://github.com/nv-nguyen/pizza","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-on-linemod","task":"6D Pose Estimation using RGB","dataset":"LineMOD","model":"PoseCNN + DeepIM","rank_in_archive_order":12,"of":22,"metrics":{"Accuracy":"97.5","Accuracy (ADD)":"88.1%","Mean ADD":"88.6"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-using-rgb-on-occlusion","task":"6D Pose Estimation using RGB","dataset":"Occlusion LineMOD","model":"DeepIM (Train on Occlusion LineMOD)","rank_in_archive_order":4,"of":13,"metrics":{"Mean ADD":"55.5"},"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 + DeepIM","rank_in_archive_order":3,"of":9,"metrics":{"Mean ADD":"80.6","Mean ADI":"92.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00175"}},"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/liyi14/mx-DeepIM","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nv-nguyen/pizza","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"293f52dd0619b909","entry":"calc_EPE_one_pair","repo":"liyi14/mx-DeepIM","repo_kind":"listed","path":"deepim/core/tester.py","file_url":"https://github.com/liyi14/mx-DeepIM/blob/HEAD/deepim/core/tester.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"293f52dd0619b909"}},{"code_sha256_prefix":"ba2dcde944b1c35c","entry":"get_flow_names_iter","repo":"liyi14/mx-DeepIM","repo_kind":"listed","path":"deepim/core/metric.py","file_url":"https://github.com/liyi14/mx-DeepIM/blob/HEAD/deepim/core/metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba2dcde944b1c35c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}