{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IUHM3HD747KWWC6UI6YTWGL64I","short_pith_number":"pith:IUHM3HD7","schema_version":"1.0","canonical_sha256":"450ecd9c7fe7d56b0bd447b13b197ee22b114c864a4f60842040dc3f244384f0","source":{"kind":"arxiv","id":"2309.16956","version":1},"attestation_state":"computed","paper":{"title":"Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawei Wang, Nenglun Chen, Ruigang Yang, Runnan Chen, Tongliang Liu, Wei Li, Wenping Wang, Xinge Zhu, Yuexin Ma","submitted_at":"2023-09-29T03:51:26Z","abstract_excerpt":"Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design (CAD) models and languages. The main challenges are the domain gaps between the CAD models and the real scene's objects, including model-to-scene (from a single model to the scene) and synthetic-to-real (from synthetic model to real scene's object). To handle the above challenges, Model2Scene first simulates a crowded scene by mixing "},"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":"2309.16956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T03:51:26Z","cross_cats_sorted":[],"title_canon_sha256":"53367045fea75abe8c52d4b099643f3fd7fbadf45d3ce214b7262133f505275a","abstract_canon_sha256":"d727a3f89ae1225efa33ea5d49532f49b2e4e48491c90e1cf22a1f1d3b157169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:30.318956Z","signature_b64":"q4Lz6NpXfdrgvarJSJIJU6SuP2eyKSPNruXfE0Cz0+6XWkms+ZIGDHIOZlxivI4XaQf0eLxpilGb8+QXkteUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450ecd9c7fe7d56b0bd447b13b197ee22b114c864a4f60842040dc3f244384f0","last_reissued_at":"2026-07-05T06:55:30.318447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:30.318447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawei Wang, Nenglun Chen, Ruigang Yang, Runnan Chen, Tongliang Liu, Wei Li, Wenping Wang, Xinge Zhu, Yuexin Ma","submitted_at":"2023-09-29T03:51:26Z","abstract_excerpt":"Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design (CAD) models and languages. The main challenges are the domain gaps between the CAD models and the real scene's objects, including model-to-scene (from a single model to the scene) and synthetic-to-real (from synthetic model to real scene's object). To handle the above challenges, Model2Scene first simulates a crowded scene by mixing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16956","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/2309.16956/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":"2309.16956","created_at":"2026-07-05T06:55:30.318506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16956v1","created_at":"2026-07-05T06:55:30.318506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16956","created_at":"2026-07-05T06:55:30.318506+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUHM3HD747KW","created_at":"2026-07-05T06:55:30.318506+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUHM3HD747KWWC6U","created_at":"2026-07-05T06:55:30.318506+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUHM3HD7","created_at":"2026-07-05T06:55:30.318506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00326","citing_title":"OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I","json":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I.json","graph_json":"https://pith.science/api/pith-number/IUHM3HD747KWWC6UI6YTWGL64I/graph.json","events_json":"https://pith.science/api/pith-number/IUHM3HD747KWWC6UI6YTWGL64I/events.json","paper":"https://pith.science/paper/IUHM3HD7"},"agent_actions":{"view_html":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I","download_json":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I.json","view_paper":"https://pith.science/paper/IUHM3HD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16956&json=true","fetch_graph":"https://pith.science/api/pith-number/IUHM3HD747KWWC6UI6YTWGL64I/graph.json","fetch_events":"https://pith.science/api/pith-number/IUHM3HD747KWWC6UI6YTWGL64I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I/action/storage_attestation","attest_author":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I/action/author_attestation","sign_citation":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I/action/citation_signature","submit_replication":"https://pith.science/pith/IUHM3HD747KWWC6UI6YTWGL64I/action/replication_record"}},"created_at":"2026-07-05T06:55:30.318506+00:00","updated_at":"2026-07-05T06:55:30.318506+00:00"}