{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6D2FXCSXYX4DLBBV2LWIFD7ZPB","short_pith_number":"pith:6D2FXCSX","schema_version":"1.0","canonical_sha256":"f0f45b8a57c5f8358435d2ec828ff97863a167e67d24f849c4deead13eb1f5d0","source":{"kind":"arxiv","id":"2411.15779","version":1},"attestation_state":"computed","paper":{"title":"ZeroGS: Training 3D Gaussian Splatting from Unposed Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Evangelos Ververas, Gim Hee Lee, Jiankang Deng, Jifei Song, Rolandos Alexandros Potamias, Yu Chen","submitted_at":"2024-11-24T11:20:48Z","abstract_excerpt":"Neural radiance fields (NeRF) and 3D Gaussian Splatting (3DGS) are popular techniques to reconstruct and render photo-realistic images. However, the pre-requisite of running Structure-from-Motion (SfM) to get camera poses limits their completeness. While previous methods can reconstruct from a few unposed images, they are not applicable when images are unordered or densely captured. In this work, we propose ZeroGS to train 3DGS from hundreds of unposed and unordered images. Our method leverages a pretrained foundation model as the neural scene representation. Since the accuracy of the predicte"},"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":"2411.15779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T11:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"0b63933064d29728b62f32579aa165ef01af7424fca8389ca5dbb7ea66b02d4b","abstract_canon_sha256":"e37cb483dc2c36fbc6c27239bebca8446f92c40c1b0f90890df076dca42bc20b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:41.020110Z","signature_b64":"epdk3F6qnYE1M1IzPZewfJaoE+GbEMgq8Gvfpdv2xivBlwU6tCNv0klr62Yq7JO8j46gRyX7+hLUa4fyR7LtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f45b8a57c5f8358435d2ec828ff97863a167e67d24f849c4deead13eb1f5d0","last_reissued_at":"2026-07-05T09:39:41.019725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:41.019725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroGS: Training 3D Gaussian Splatting from Unposed Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Evangelos Ververas, Gim Hee Lee, Jiankang Deng, Jifei Song, Rolandos Alexandros Potamias, Yu Chen","submitted_at":"2024-11-24T11:20:48Z","abstract_excerpt":"Neural radiance fields (NeRF) and 3D Gaussian Splatting (3DGS) are popular techniques to reconstruct and render photo-realistic images. However, the pre-requisite of running Structure-from-Motion (SfM) to get camera poses limits their completeness. While previous methods can reconstruct from a few unposed images, they are not applicable when images are unordered or densely captured. In this work, we propose ZeroGS to train 3DGS from hundreds of unposed and unordered images. Our method leverages a pretrained foundation model as the neural scene representation. Since the accuracy of the predicte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15779","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/2411.15779/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":"2411.15779","created_at":"2026-07-05T09:39:41.019778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15779v1","created_at":"2026-07-05T09:39:41.019778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15779","created_at":"2026-07-05T09:39:41.019778+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D2FXCSXYX4D","created_at":"2026-07-05T09:39:41.019778+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D2FXCSXYX4DLBBV","created_at":"2026-07-05T09:39:41.019778+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D2FXCSX","created_at":"2026-07-05T09:39:41.019778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21960","citing_title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB","json":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB.json","graph_json":"https://pith.science/api/pith-number/6D2FXCSXYX4DLBBV2LWIFD7ZPB/graph.json","events_json":"https://pith.science/api/pith-number/6D2FXCSXYX4DLBBV2LWIFD7ZPB/events.json","paper":"https://pith.science/paper/6D2FXCSX"},"agent_actions":{"view_html":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB","download_json":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB.json","view_paper":"https://pith.science/paper/6D2FXCSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15779&json=true","fetch_graph":"https://pith.science/api/pith-number/6D2FXCSXYX4DLBBV2LWIFD7ZPB/graph.json","fetch_events":"https://pith.science/api/pith-number/6D2FXCSXYX4DLBBV2LWIFD7ZPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB/action/storage_attestation","attest_author":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB/action/author_attestation","sign_citation":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB/action/citation_signature","submit_replication":"https://pith.science/pith/6D2FXCSXYX4DLBBV2LWIFD7ZPB/action/replication_record"}},"created_at":"2026-07-05T09:39:41.019778+00:00","updated_at":"2026-07-05T09:39:41.019778+00:00"}