{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZFSDPYR2O4HYI4LDI7ORJHCZ67","short_pith_number":"pith:ZFSDPYR2","schema_version":"1.0","canonical_sha256":"c96437e23a770f84716347dd149c59f7fdeda8b438b385d8a5102c734b98c940","source":{"kind":"arxiv","id":"2406.10324","version":1},"attestation_state":"computed","paper":{"title":"L4GM: Large 4D Gaussian Reconstruction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Ashkan Mirzaei, Hanxue Liang, Huan Ling, Jiawei Ren, Karsten Kreis, Kevin Xie, Sanja Fidler, Seung Wook Kim, Xiaohui Zeng, Ziwei Liu","submitted_at":"2024-06-14T17:51:18Z","abstract_excerpt":"We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from mu"},"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":"2406.10324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:51:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3529b3ecdc1d36aa076db88365f4d9e49c86907e8033e16fe7191e9423bc8549","abstract_canon_sha256":"af24d34ae7d2e54e31c281f3b801aa8350a99f43d6e4059d77443293b23552e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:14.999349Z","signature_b64":"BP0bqK/wArNw/Q4A3vZgUA3VtPtn+CNvFNciuEVtYcGdD3GZwIqcnJn3HXE9jJg8a2ZLX1C9ujZ+a/gka1mtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c96437e23a770f84716347dd149c59f7fdeda8b438b385d8a5102c734b98c940","last_reissued_at":"2026-07-05T08:32:14.998835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:14.998835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L4GM: Large 4D Gaussian Reconstruction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Ashkan Mirzaei, Hanxue Liang, Huan Ling, Jiawei Ren, Karsten Kreis, Kevin Xie, Sanja Fidler, Seung Wook Kim, Xiaohui Zeng, Ziwei Liu","submitted_at":"2024-06-14T17:51:18Z","abstract_excerpt":"We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10324","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/2406.10324/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":"2406.10324","created_at":"2026-07-05T08:32:14.998905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10324v1","created_at":"2026-07-05T08:32:14.998905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10324","created_at":"2026-07-05T08:32:14.998905+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFSDPYR2O4HY","created_at":"2026-07-05T08:32:14.998905+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFSDPYR2O4HYI4LD","created_at":"2026-07-05T08:32:14.998905+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFSDPYR2","created_at":"2026-07-05T08:32:14.998905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25344","citing_title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17623","citing_title":"ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15239","citing_title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17623","citing_title":"ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67","json":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67.json","graph_json":"https://pith.science/api/pith-number/ZFSDPYR2O4HYI4LDI7ORJHCZ67/graph.json","events_json":"https://pith.science/api/pith-number/ZFSDPYR2O4HYI4LDI7ORJHCZ67/events.json","paper":"https://pith.science/paper/ZFSDPYR2"},"agent_actions":{"view_html":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67","download_json":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67.json","view_paper":"https://pith.science/paper/ZFSDPYR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10324&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFSDPYR2O4HYI4LDI7ORJHCZ67/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFSDPYR2O4HYI4LDI7ORJHCZ67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67/action/storage_attestation","attest_author":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67/action/author_attestation","sign_citation":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67/action/citation_signature","submit_replication":"https://pith.science/pith/ZFSDPYR2O4HYI4LDI7ORJHCZ67/action/replication_record"}},"created_at":"2026-07-05T08:32:14.998905+00:00","updated_at":"2026-07-05T08:32:14.998905+00:00"}