{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LCWO7EEM3VFL3BT5B77AZF2MNU","short_pith_number":"pith:LCWO7EEM","schema_version":"1.0","canonical_sha256":"58acef908cdd4abd867d0ffe0c974c6d3d38ca1eb8e3f703d445f55a3365f9f3","source":{"kind":"arxiv","id":"2304.00947","version":2},"attestation_state":"computed","paper":{"title":"RePAST: Relative Pose Attention Scene Representation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aleksandr Safin, Daniel Duckworth, Mehdi S. M. Sajjadi","submitted_at":"2023-04-03T13:13:12Z","abstract_excerpt":"The Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates. Since SRT uses camera poses with respect to an arbitrarily chosen reference camera, it is not invariant to the order of the input views. As a result, SRT is not directly applicable to large-scale scenes where the reference frame would need to be changed regularly. In this work, we propose Relative Pose Attention SRT (RePAST): Instead of fixing a reference frame at the input, we inject pairwise relative camera pose information directly into the attention mechanism of the Transformers. This "},"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":"2304.00947","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T13:13:12Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.RO"],"title_canon_sha256":"c4605b7222e49ce9d6aab6f5a0f188e09da76018c0eb6cfc9099883248176c88","abstract_canon_sha256":"ffa89d78cb0bbe0f14b898a4dffcfa7f7992ec59729e3ddfaeaf7f20b484b257"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:24.172263Z","signature_b64":"IcgB7Y+7hGeS7toFHhY0/Mh682u55tI8+AsYrCkmItZy0JfMEf2f2Dtmv4e/I4UjMcnjT+Q4CTDqrd4G6g/zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58acef908cdd4abd867d0ffe0c974c6d3d38ca1eb8e3f703d445f55a3365f9f3","last_reissued_at":"2026-07-05T05:59:24.171763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:24.171763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RePAST: Relative Pose Attention Scene Representation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aleksandr Safin, Daniel Duckworth, Mehdi S. M. Sajjadi","submitted_at":"2023-04-03T13:13:12Z","abstract_excerpt":"The Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates. Since SRT uses camera poses with respect to an arbitrarily chosen reference camera, it is not invariant to the order of the input views. As a result, SRT is not directly applicable to large-scale scenes where the reference frame would need to be changed regularly. In this work, we propose Relative Pose Attention SRT (RePAST): Instead of fixing a reference frame at the input, we inject pairwise relative camera pose information directly into the attention mechanism of the Transformers. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00947","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/2304.00947/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":"2304.00947","created_at":"2026-07-05T05:59:24.171822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00947v2","created_at":"2026-07-05T05:59:24.171822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00947","created_at":"2026-07-05T05:59:24.171822+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCWO7EEM3VFL","created_at":"2026-07-05T05:59:24.171822+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCWO7EEM3VFL3BT5","created_at":"2026-07-05T05:59:24.171822+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCWO7EEM","created_at":"2026-07-05T05:59:24.171822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":221,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU","json":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU.json","graph_json":"https://pith.science/api/pith-number/LCWO7EEM3VFL3BT5B77AZF2MNU/graph.json","events_json":"https://pith.science/api/pith-number/LCWO7EEM3VFL3BT5B77AZF2MNU/events.json","paper":"https://pith.science/paper/LCWO7EEM"},"agent_actions":{"view_html":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU","download_json":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU.json","view_paper":"https://pith.science/paper/LCWO7EEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00947&json=true","fetch_graph":"https://pith.science/api/pith-number/LCWO7EEM3VFL3BT5B77AZF2MNU/graph.json","fetch_events":"https://pith.science/api/pith-number/LCWO7EEM3VFL3BT5B77AZF2MNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU/action/storage_attestation","attest_author":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU/action/author_attestation","sign_citation":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU/action/citation_signature","submit_replication":"https://pith.science/pith/LCWO7EEM3VFL3BT5B77AZF2MNU/action/replication_record"}},"created_at":"2026-07-05T05:59:24.171822+00:00","updated_at":"2026-07-05T05:59:24.171822+00:00"}