{"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/deep-part-induction-from-articulated-object","title":"Deep Part Induction from Articulated Object Pairs","arxiv_id":"1809.07417","date":"2018-09-19","proceeding":null,"authors":["Li Yi","Haibin Huang","Difan Liu","Evangelos Kalogerakis","Hao Su","Leonidas Guibas"],"abstract":"Object functionality is often expressed through part articulation -- as when\nthe two rigid parts of a scissor pivot against each other to perform the\ncutting function. Such articulations are often similar across objects within\nthe same functional category. In this paper, we explore how the observation of\ndifferent articulation states provides evidence for part structure and motion\nof 3D objects. Our method takes as input a pair of unsegmented shapes\nrepresenting two different articulation states of two functionally related\nobjects, and induces their common parts along with their underlying rigid\nmotion. This is a challenging setting, as we assume no prior shape structure,\nno prior shape category information, no consistent shape orientation, the\narticulation states may belong to objects of different geometry, plus we allow\ninputs to be noisy and partial scans, or point clouds lifted from RGB images.\nOur method learns a neural network architecture with three modules that\nrespectively propose correspondences, estimate 3D deformation flows, and\nperform segmentation. To achieve optimal performance, our architecture\nalternates between correspondence, deformation flow, and segmentation\nprediction iteratively in an ICP-like fashion. Our results demonstrate that our\nmethod significantly outperforms state-of-the-art techniques in the task of\ndiscovering articulated parts of objects. In addition, our part induction is\nobject-class agnostic and successfully generalizes to new and unseen objects.","url_abs":"http://arxiv.org/abs/1809.07417v1","url_pdf":"http://arxiv.org/pdf/1809.07417v1.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":"deep-part-induction-from-articulated-object","repo_url":"https://github.com/ericyi/articulated-part-induction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.07417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07417"}},"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/ericyi/articulated-part-induction","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"2d5ecd955f306173","entry":"get_batch_data","repo":"ericyi/articulated-part-induction","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/ericyi/articulated-part-induction/blob/HEAD/evaluation.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":"2d5ecd955f306173"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}