{"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/scan2cad-learning-cad-model-alignment-in-rgb","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","arxiv_id":"1811.11187","date":"2018-11-27","proceeding":"CVPR 2019 6","authors":["Armen Avetisyan","Manuel Dahnert","Angela Dai","Manolis Savva","Angel X. Chang","Matthias Nießner"],"abstract":"We present Scan2CAD, a novel data-driven method that learns to align clean 3D\nCAD models from a shape database to the noisy and incomplete geometry of a\ncommodity RGB-D scan. For a 3D reconstruction of an indoor scene, our method\ntakes as input a set of CAD models, and predicts a 9DoF pose that aligns each\nmodel to the underlying scan geometry. To tackle this problem, we create a new\nscan-to-CAD alignment dataset based on 1506 ScanNet scans with 97607 annotated\nkeypoint pairs between 14225 CAD models from ShapeNet and their counterpart\nobjects in the scans. Our method selects a set of representative keypoints in a\n3D scan for which we find correspondences to the CAD geometry. To this end, we\ndesign a novel 3D CNN architecture that learns a joint embedding between real\nand synthetic objects, and from this predicts a correspondence heatmap. Based\non these correspondence heatmaps, we formulate a variational energy\nminimization that aligns a given set of CAD models to the reconstruction. We\nevaluate our approach on our newly introduced Scan2CAD benchmark where we\noutperform both handcrafted feature descriptor as well as state-of-the-art CNN\nbased methods by 21.39%.","url_abs":"http://arxiv.org/abs/1811.11187v1","url_pdf":"http://arxiv.org/pdf/1811.11187v1.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":"scan2cad-learning-cad-model-alignment-in-rgb","repo_url":"https://github.com/skanti/Scan2CAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scan2cad-learning-cad-model-alignment-in-rgb","repo_url":"https://github.com/skanti/Scan2CAD-Annotation-Webapp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"}],"methods":[],"datasets_introduced":[{"slug":"scan2cad","name":"Scan2CAD","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-reconstruction-on-scan2cad","task":"3D Reconstruction","dataset":"Scan2CAD","model":"Scan2CAD","rank_in_archive_order":1,"of":2,"metrics":{"Average Accuracy":"31.68%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.11187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11187"}},"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/skanti/Scan2CAD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/skanti/Scan2CAD-Annotation-Webapp","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"fce873dc31a28381","entry":"get_catid2index","repo":"skanti/Scan2CAD","repo_kind":"listed","path":"Routines/Script/Annotation2Mesh.py","file_url":"https://github.com/skanti/Scan2CAD/blob/HEAD/Routines/Script/Annotation2Mesh.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fce873dc31a28381"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}