{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SHWIRG7AXQJSKLE3YEKXUUI4TW","short_pith_number":"pith:SHWIRG7A","schema_version":"1.0","canonical_sha256":"91ec889be0bc13252c9bc1157a511c9da9587e2816ea6487ea83767cbf1b6fc7","source":{"kind":"arxiv","id":"2412.09008","version":1},"attestation_state":"computed","paper":{"title":"MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.MM"],"primary_cat":"cs.CV","authors_text":"Pheng-Ann Heng, Ruiyang Li, Shi Qiu, Yue Qiu, Yuqi Tong","submitted_at":"2024-12-12T07:20:32Z","abstract_excerpt":"We present MS2Mesh-XR, a novel multi-modal sketch-to-mesh generation pipeline that enables users to create realistic 3D objects in extended reality (XR) environments using hand-drawn sketches assisted by voice inputs. In specific, users can intuitively sketch objects using natural hand movements in mid-air within a virtual environment. By integrating voice inputs, we devise ControlNet to infer realistic images based on the drawn sketches and interpreted text prompts. Users can then review and select their preferred image, which is subsequently reconstructed into a detailed 3D mesh using the Co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.09008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T07:20:32Z","cross_cats_sorted":["cs.HC","cs.MM"],"title_canon_sha256":"3f8a55ae0bff7fec181c004ee4336a23f4fec867574abd7d618f70aae4070bdd","abstract_canon_sha256":"91108c6a0b1fd157825ad02b703e5fcb094445e86cb1855fcf5d7d8fb1c35463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:05.325757Z","signature_b64":"aHR+TCygXqaaTwDjZtflKlBIY+hRxZBf2RW/PTKM7Fd/SbC2Wt6gMv9vauVIojyu7BYUmRUi7i1TjBO0SBpEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91ec889be0bc13252c9bc1157a511c9da9587e2816ea6487ea83767cbf1b6fc7","last_reissued_at":"2026-07-05T09:48:05.325292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:05.325292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.MM"],"primary_cat":"cs.CV","authors_text":"Pheng-Ann Heng, Ruiyang Li, Shi Qiu, Yue Qiu, Yuqi Tong","submitted_at":"2024-12-12T07:20:32Z","abstract_excerpt":"We present MS2Mesh-XR, a novel multi-modal sketch-to-mesh generation pipeline that enables users to create realistic 3D objects in extended reality (XR) environments using hand-drawn sketches assisted by voice inputs. In specific, users can intuitively sketch objects using natural hand movements in mid-air within a virtual environment. By integrating voice inputs, we devise ControlNet to infer realistic images based on the drawn sketches and interpreted text prompts. Users can then review and select their preferred image, which is subsequently reconstructed into a detailed 3D mesh using the Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09008","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.09008/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.09008","created_at":"2026-07-05T09:48:05.325358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09008v1","created_at":"2026-07-05T09:48:05.325358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09008","created_at":"2026-07-05T09:48:05.325358+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHWIRG7AXQJS","created_at":"2026-07-05T09:48:05.325358+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHWIRG7AXQJSKLE3","created_at":"2026-07-05T09:48:05.325358+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHWIRG7A","created_at":"2026-07-05T09:48:05.325358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07894","citing_title":"SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW","json":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW.json","graph_json":"https://pith.science/api/pith-number/SHWIRG7AXQJSKLE3YEKXUUI4TW/graph.json","events_json":"https://pith.science/api/pith-number/SHWIRG7AXQJSKLE3YEKXUUI4TW/events.json","paper":"https://pith.science/paper/SHWIRG7A"},"agent_actions":{"view_html":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW","download_json":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW.json","view_paper":"https://pith.science/paper/SHWIRG7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09008&json=true","fetch_graph":"https://pith.science/api/pith-number/SHWIRG7AXQJSKLE3YEKXUUI4TW/graph.json","fetch_events":"https://pith.science/api/pith-number/SHWIRG7AXQJSKLE3YEKXUUI4TW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW/action/storage_attestation","attest_author":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW/action/author_attestation","sign_citation":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW/action/citation_signature","submit_replication":"https://pith.science/pith/SHWIRG7AXQJSKLE3YEKXUUI4TW/action/replication_record"}},"created_at":"2026-07-05T09:48:05.325358+00:00","updated_at":"2026-07-05T09:48:05.325358+00:00"}