{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IC43MXKATVCXOGUH4HML7AHCIY","short_pith_number":"pith:IC43MXKA","schema_version":"1.0","canonical_sha256":"40b9b65d409d45771a87e1d8bf80e246049b36803d3c457d247dc6da341c60ba","source":{"kind":"arxiv","id":"2412.01553","version":1},"attestation_state":"computed","paper":{"title":"SfM-Free 3D Gaussian Splatting via Hierarchical Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Bo Ji","submitted_at":"2024-12-02T14:39:06Z","abstract_excerpt":"Standard 3D Gaussian Splatting (3DGS) relies on known or pre-computed camera poses and a sparse point cloud, obtained from structure-from-motion (SfM) preprocessing, to initialize and grow 3D Gaussians. We propose a novel SfM-Free 3DGS (SFGS) method for video input, eliminating the need for known camera poses and SfM preprocessing. Our approach introduces a hierarchical training strategy that trains and merges multiple 3D Gaussian representations -- each optimized for specific scene regions -- into a single, unified 3DGS model representing the entire scene. To compensate for large camera motio"},"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":"2412.01553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T14:39:06Z","cross_cats_sorted":[],"title_canon_sha256":"e0213535d6c41c6361d608ab5f79967af8ddfc15ca976fe3d55f23a1670ef968","abstract_canon_sha256":"629ccd96b93208a7a39953f8c3e66b28cf301eb5c9d2d67704345280549759c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:14.904785Z","signature_b64":"Bz66SDGRlw6FgRaBDFKJw+BpTxlAmvfFwEAJKProkL831lwGDWyNKpkVO4wuR12vj8xj6IUGZp2V8xyqbLzLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40b9b65d409d45771a87e1d8bf80e246049b36803d3c457d247dc6da341c60ba","last_reissued_at":"2026-07-05T09:43:14.904298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:14.904298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SfM-Free 3D Gaussian Splatting via Hierarchical Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Bo Ji","submitted_at":"2024-12-02T14:39:06Z","abstract_excerpt":"Standard 3D Gaussian Splatting (3DGS) relies on known or pre-computed camera poses and a sparse point cloud, obtained from structure-from-motion (SfM) preprocessing, to initialize and grow 3D Gaussians. We propose a novel SfM-Free 3DGS (SFGS) method for video input, eliminating the need for known camera poses and SfM preprocessing. Our approach introduces a hierarchical training strategy that trains and merges multiple 3D Gaussian representations -- each optimized for specific scene regions -- into a single, unified 3DGS model representing the entire scene. To compensate for large camera motio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01553","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/2412.01553/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":"2412.01553","created_at":"2026-07-05T09:43:14.904366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01553v1","created_at":"2026-07-05T09:43:14.904366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01553","created_at":"2026-07-05T09:43:14.904366+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC43MXKATVCX","created_at":"2026-07-05T09:43:14.904366+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC43MXKATVCXOGUH","created_at":"2026-07-05T09:43:14.904366+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC43MXKA","created_at":"2026-07-05T09:43:14.904366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14041","citing_title":"LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY","json":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY.json","graph_json":"https://pith.science/api/pith-number/IC43MXKATVCXOGUH4HML7AHCIY/graph.json","events_json":"https://pith.science/api/pith-number/IC43MXKATVCXOGUH4HML7AHCIY/events.json","paper":"https://pith.science/paper/IC43MXKA"},"agent_actions":{"view_html":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY","download_json":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY.json","view_paper":"https://pith.science/paper/IC43MXKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01553&json=true","fetch_graph":"https://pith.science/api/pith-number/IC43MXKATVCXOGUH4HML7AHCIY/graph.json","fetch_events":"https://pith.science/api/pith-number/IC43MXKATVCXOGUH4HML7AHCIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY/action/storage_attestation","attest_author":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY/action/author_attestation","sign_citation":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY/action/citation_signature","submit_replication":"https://pith.science/pith/IC43MXKATVCXOGUH4HML7AHCIY/action/replication_record"}},"created_at":"2026-07-05T09:43:14.904366+00:00","updated_at":"2026-07-05T09:43:14.904366+00:00"}