{"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/gigapose-fast-and-robust-novel-object-pose","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","arxiv_id":"2311.14155","date":"2023-11-23","proceeding":"CVPR 2024 1","authors":["Van Nguyen Nguyen","Thibault Groueix","Mathieu Salzmann","Vincent Lepetit"],"abstract":"We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative \"templates\", rendered images of the CAD models, to recover the out-of-plane rotation and then uses patch correspondences to estimate the four remaining parameters. Our approach samples templates in only a two-degrees-of-freedom space instead of the usual three and matches the input image to the templates using fast nearest-neighbor search in feature space, results in a speedup factor of 35x compared to the state of the art. Moreover, GigaPose is significantly more robust to segmentation errors. Our extensive evaluation on the seven core datasets of the BOP challenge demonstrates that it achieves state-of-the-art accuracy and can be seamlessly integrated with existing refinement methods. Additionally, we show the potential of GigaPose with 3D models predicted by recent work on 3D reconstruction from a single image, relaxing the need for CAD models and making 6D pose object estimation much more convenient. Our source code and trained models are publicly available at https://github.com/nv-nguyen/gigaPose","url_abs":"https://arxiv.org/abs/2311.14155v2","url_pdf":"https://arxiv.org/pdf/2311.14155v2.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":"gigapose-fast-and-robust-novel-object-pose","repo_url":"https://github.com/nv-nguyen/gigapose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"6d-pose-estimation-1","task_name":"6D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-on-dttd2","task":"6D Pose Estimation","dataset":"DTTD-Mobile","model":"GigaPose","rank_in_archive_order":6,"of":8,"metrics":{"AR CH":"12.16","AR CoU":"39.32","AR pCH":"74"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.14155","atlas_url":"https://app.syntology.ai/?focus=2311.14155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14155"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/nv-nguyen/gigapose","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"b7feb9d20d41b6d4","entry":"look_at","repo":"nv-nguyen/gigapose","repo_kind":"official","path":"src/lib3d/create_template_poses.py","file_url":"https://github.com/nv-nguyen/gigapose/blob/HEAD/src/lib3d/create_template_poses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7feb9d20d41b6d4"}},{"code_sha256_prefix":"096ef91a9442bde2","entry":"normalize","repo":"nv-nguyen/gigapose","repo_kind":"official","path":"src/lib3d/create_template_poses.py","file_url":"https://github.com/nv-nguyen/gigapose/blob/HEAD/src/lib3d/create_template_poses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"096ef91a9442bde2"}},{"code_sha256_prefix":"b6ef71ad09abc9d9","entry":"load_cfg","repo":"nv-nguyen/gigapose","repo_kind":"official","path":"src/custom_megapose/refiner_utils.py","file_url":"https://github.com/nv-nguyen/gigapose/blob/HEAD/src/custom_megapose/refiner_utils.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":"b6ef71ad09abc9d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}