{"paper":{"title":"Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Users can articulate 3D CAD models by drawing simple 2D sketches from one viewpoint, which the system turns into movable parts and motion parameters.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Alla Sheffer, Changjian Li, Hao Pan, Yijing Cui, Yi Yang","submitted_at":"2026-04-28T15:47:30Z","abstract_excerpt":"Articulation modeling aims to infer movable parts and their motion parameters for a 3D object, enabling interactive animation, simulation, and shape editing. In this paper, we present Sketch2Arti, the first sketch-based articulation modeling system for CAD objects. Our key observation is that designers naturally communicate articulation intent through lightweight sketches (e.g., arrows and strokes) that indicate how parts should move, yet translating such sketches into articulated 3D models remains largely manual. Sketch2Arti bridges this gap by enabling users to specify articulation through s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Sketch2Arti is the first sketch-based articulation modeling system for CAD objects that automatically discovers movable parts and predicts motion parameters from simple 2D sketches, trained category-agnostically with strong generalization and support for controllable internal completion on shell models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That 2D sketches drawn from a single viewpoint reliably encode the user's 3D articulation intent and that the learned model can correctly map those sketches to accurate 3D motion parameters and internal structures without category-specific information or explicit 3D supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sketch2Arti is the first category-agnostic sketch-based system that infers movable parts and motion parameters from 2D user sketches on CAD objects and supports sketch-guided internal structure completion for shell models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Users can articulate 3D CAD models by drawing simple 2D sketches from one viewpoint, which the system turns into movable parts and motion parameters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2d6e352982abe63385a1ebc50502333632c13d13d6b84868ea68a295e1a6a611"},"source":{"id":"2604.25781","kind":"arxiv","version":2},"verdict":{"id":"a5a2be0a-6c17-42eb-960a-c08fa162fe9d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T16:44:41.185210Z","strongest_claim":"Sketch2Arti is the first sketch-based articulation modeling system for CAD objects that automatically discovers movable parts and predicts motion parameters from simple 2D sketches, trained category-agnostically with strong generalization and support for controllable internal completion on shell models.","one_line_summary":"Sketch2Arti is the first category-agnostic sketch-based system that infers movable parts and motion parameters from 2D user sketches on CAD objects and supports sketch-guided internal structure completion for shell models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That 2D sketches drawn from a single viewpoint reliably encode the user's 3D articulation intent and that the learned model can correctly map those sketches to accurate 3D motion parameters and internal structures without category-specific information or explicit 3D supervision.","pith_extraction_headline":"Users can articulate 3D CAD models by drawing simple 2D sketches from one viewpoint, which the system turns into movable parts and motion parameters."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.25781/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T04:33:58.982217Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:46:46.607884Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"02814075f832b4ce68811f7681ca72bcfe9382fb3d6d82a9a9686df78db56bcb"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}