{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PZJOYWCMXWDE5WXBZKHFDGXD24","short_pith_number":"pith:PZJOYWCM","schema_version":"1.0","canonical_sha256":"7e52ec584cbd864edae1ca8e519ae3d706631e02ba9b12d4b00fd6b75be33c37","source":{"kind":"arxiv","id":"2311.12024","version":2},"attestation_state":"computed","paper":{"title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Hao Tan, Kai Zhang, Kalyan Sunkavalli, Peng Wang, Sai Bi, Wenping Wang, Yinghao Xu, Zexiang Xu","submitted_at":"2023-11-20T18:57:55Z","abstract_excerpt":"We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1.3 seconds on a single A100 GPU. PF-LRM is a highly scalable method utilizing the self-attention blocks to exchange information between 3D object tokens and 2D image tokens; we predict a coarse point cloud for each view, and then use a differentiable Perspective-n-Point (PnP) solver to obtain camera poses. When trained on a huge amount of multi-view posed data of ~1M objects, PF-LRM sh"},"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":"2311.12024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T18:57:55Z","cross_cats_sorted":[],"title_canon_sha256":"686b067eef33cf1ee7b318f1c5930a4056ecbeec2562f98a503b189c5bc84da3","abstract_canon_sha256":"161a16ff99e4762fcb89f640168488b6f4513b94cb512de610adf92dd6ce1456"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:04.495162Z","signature_b64":"T8XXhadY0FU24bWbhmoTcuaQfgUbglvCRxvA48WP/YTedjKFqTc+YeEmkNBV5wpYdYKP4iuQ4VlVYIaGGJw1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e52ec584cbd864edae1ca8e519ae3d706631e02ba9b12d4b00fd6b75be33c37","last_reissued_at":"2026-07-05T07:16:04.494596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:04.494596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Hao Tan, Kai Zhang, Kalyan Sunkavalli, Peng Wang, Sai Bi, Wenping Wang, Yinghao Xu, Zexiang Xu","submitted_at":"2023-11-20T18:57:55Z","abstract_excerpt":"We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1.3 seconds on a single A100 GPU. PF-LRM is a highly scalable method utilizing the self-attention blocks to exchange information between 3D object tokens and 2D image tokens; we predict a coarse point cloud for each view, and then use a differentiable Perspective-n-Point (PnP) solver to obtain camera poses. When trained on a huge amount of multi-view posed data of ~1M objects, PF-LRM sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12024","kind":"arxiv","version":2},"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/2311.12024/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":"2311.12024","created_at":"2026-07-05T07:16:04.494652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12024v2","created_at":"2026-07-05T07:16:04.494652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12024","created_at":"2026-07-05T07:16:04.494652+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZJOYWCMXWDE","created_at":"2026-07-05T07:16:04.494652+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZJOYWCMXWDE5WXB","created_at":"2026-07-05T07:16:04.494652+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZJOYWCM","created_at":"2026-07-05T07:16:04.494652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25476","citing_title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00321","citing_title":"CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2411.13549","citing_title":"KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2403.02151","citing_title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24","json":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24.json","graph_json":"https://pith.science/api/pith-number/PZJOYWCMXWDE5WXBZKHFDGXD24/graph.json","events_json":"https://pith.science/api/pith-number/PZJOYWCMXWDE5WXBZKHFDGXD24/events.json","paper":"https://pith.science/paper/PZJOYWCM"},"agent_actions":{"view_html":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24","download_json":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24.json","view_paper":"https://pith.science/paper/PZJOYWCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12024&json=true","fetch_graph":"https://pith.science/api/pith-number/PZJOYWCMXWDE5WXBZKHFDGXD24/graph.json","fetch_events":"https://pith.science/api/pith-number/PZJOYWCMXWDE5WXBZKHFDGXD24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24/action/storage_attestation","attest_author":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24/action/author_attestation","sign_citation":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24/action/citation_signature","submit_replication":"https://pith.science/pith/PZJOYWCMXWDE5WXBZKHFDGXD24/action/replication_record"}},"created_at":"2026-07-05T07:16:04.494652+00:00","updated_at":"2026-07-05T07:16:04.494652+00:00"}