{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U4XWGHQADWGCB4MISEITGMZLGM","short_pith_number":"pith:U4XWGHQA","schema_version":"1.0","canonical_sha256":"a72f631e001d8c20f188911133332b330b91627fc1d985a87fd3aff17cbf4b46","source":{"kind":"arxiv","id":"2508.20063","version":1},"attestation_state":"computed","paper":{"title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Y. C. Chen, Cheng-Hao Kuo, Fu-En Wang, Ke Zhang, Ming-Feng Li, Min Sun, Peng-Hao Hsu, Tao Tu, Yu-Lun Liu","submitted_at":"2025-08-27T17:17:00Z","abstract_excerpt":"Open-vocabulary (OV) 3D object detection is an emerging field, yet its exploration through image-based methods remains limited compared to 3D point cloud-based methods. We introduce OpenM3D, a novel open-vocabulary multi-view indoor 3D object detector trained without human annotations. In particular, OpenM3D is a single-stage detector adapting the 2D-induced voxel features from the ImGeoNet model. To support OV, it is jointly trained with a class-agnostic 3D localization loss requiring high-quality 3D pseudo boxes and a voxel-semantic alignment loss requiring diverse pre-trained CLIP features."},"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":"2508.20063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T17:17:00Z","cross_cats_sorted":[],"title_canon_sha256":"699f7b9e18c4a111f72d13bb65a5e9e1ff9d83288d651d95caa06468a2cff090","abstract_canon_sha256":"50ffae40ce74aff6a063338550211cfa4df3c7441ea319f4804d27fdd743dec3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:23.566098Z","signature_b64":"QtDk50uyO9HFtw95/TeK/wMrnQg5Q/qs51Df2MnzSfQjKh0ZyCFWEVDGm1F1VKPzzBbri12UAzWLKL7MHCkyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a72f631e001d8c20f188911133332b330b91627fc1d985a87fd3aff17cbf4b46","last_reissued_at":"2026-07-05T12:00:23.565595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:23.565595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Y. C. Chen, Cheng-Hao Kuo, Fu-En Wang, Ke Zhang, Ming-Feng Li, Min Sun, Peng-Hao Hsu, Tao Tu, Yu-Lun Liu","submitted_at":"2025-08-27T17:17:00Z","abstract_excerpt":"Open-vocabulary (OV) 3D object detection is an emerging field, yet its exploration through image-based methods remains limited compared to 3D point cloud-based methods. We introduce OpenM3D, a novel open-vocabulary multi-view indoor 3D object detector trained without human annotations. In particular, OpenM3D is a single-stage detector adapting the 2D-induced voxel features from the ImGeoNet model. To support OV, it is jointly trained with a class-agnostic 3D localization loss requiring high-quality 3D pseudo boxes and a voxel-semantic alignment loss requiring diverse pre-trained CLIP features."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20063","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/2508.20063/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":"2508.20063","created_at":"2026-07-05T12:00:23.565654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20063v1","created_at":"2026-07-05T12:00:23.565654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20063","created_at":"2026-07-05T12:00:23.565654+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4XWGHQADWGC","created_at":"2026-07-05T12:00:23.565654+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4XWGHQADWGCB4MI","created_at":"2026-07-05T12:00:23.565654+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4XWGHQA","created_at":"2026-07-05T12:00:23.565654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM","json":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM.json","graph_json":"https://pith.science/api/pith-number/U4XWGHQADWGCB4MISEITGMZLGM/graph.json","events_json":"https://pith.science/api/pith-number/U4XWGHQADWGCB4MISEITGMZLGM/events.json","paper":"https://pith.science/paper/U4XWGHQA"},"agent_actions":{"view_html":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM","download_json":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM.json","view_paper":"https://pith.science/paper/U4XWGHQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20063&json=true","fetch_graph":"https://pith.science/api/pith-number/U4XWGHQADWGCB4MISEITGMZLGM/graph.json","fetch_events":"https://pith.science/api/pith-number/U4XWGHQADWGCB4MISEITGMZLGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM/action/storage_attestation","attest_author":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM/action/author_attestation","sign_citation":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM/action/citation_signature","submit_replication":"https://pith.science/pith/U4XWGHQADWGCB4MISEITGMZLGM/action/replication_record"}},"created_at":"2026-07-05T12:00:23.565654+00:00","updated_at":"2026-07-05T12:00:23.565654+00:00"}