{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZGJCF4QI25FELWDWWH4ZU6M4V2","short_pith_number":"pith:ZGJCF4QI","schema_version":"1.0","canonical_sha256":"c99222f208d74a45d876b1f99a799cae836a669264ebfe53eb9ede7150f0bee4","source":{"kind":"arxiv","id":"2110.00966","version":2},"attestation_state":"computed","paper":{"title":"Translating Images into Maps","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Avishkar Saha, Chris Russell, Oscar Mendez Maldonado, Richard Bowden","submitted_at":"2021-10-03T09:52:46Z","abstract_excerpt":"We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network. We assume a 1-1 correspondence between a vertical scanline in the image, and rays passing through the camera location in an overhead map. This lets us formulate map generation from an image as a set of sequence-to-sequence translations. Posing the problem as translation allows the network to use the"},"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":"2110.00966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-03T09:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"26c6641c2198b954303b673eaba928df3a244af9d855e1307f2dc3c91e324273","abstract_canon_sha256":"f3c59266c20932a8b71abeecd721c5955b3807afaf574199df883f329382685a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:58.184709Z","signature_b64":"vv3PPuo81+0fXVBrdCFzEreoaPel+CeozbMTgqBRDgmC2nL2JDTkrZlxmhkUG+AlDYka5KclNSKG1l/euza1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99222f208d74a45d876b1f99a799cae836a669264ebfe53eb9ede7150f0bee4","last_reissued_at":"2026-07-05T04:09:58.184251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:58.184251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Translating Images into Maps","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Avishkar Saha, Chris Russell, Oscar Mendez Maldonado, Richard Bowden","submitted_at":"2021-10-03T09:52:46Z","abstract_excerpt":"We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network. We assume a 1-1 correspondence between a vertical scanline in the image, and rays passing through the camera location in an overhead map. This lets us formulate map generation from an image as a set of sequence-to-sequence translations. Posing the problem as translation allows the network to use the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00966","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/2110.00966/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":"2110.00966","created_at":"2026-07-05T04:09:58.184311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00966v2","created_at":"2026-07-05T04:09:58.184311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00966","created_at":"2026-07-05T04:09:58.184311+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGJCF4QI25FE","created_at":"2026-07-05T04:09:58.184311+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGJCF4QI25FELWDW","created_at":"2026-07-05T04:09:58.184311+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGJCF4QI","created_at":"2026-07-05T04:09:58.184311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06687","citing_title":"StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2","json":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2.json","graph_json":"https://pith.science/api/pith-number/ZGJCF4QI25FELWDWWH4ZU6M4V2/graph.json","events_json":"https://pith.science/api/pith-number/ZGJCF4QI25FELWDWWH4ZU6M4V2/events.json","paper":"https://pith.science/paper/ZGJCF4QI"},"agent_actions":{"view_html":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2","download_json":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2.json","view_paper":"https://pith.science/paper/ZGJCF4QI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00966&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGJCF4QI25FELWDWWH4ZU6M4V2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGJCF4QI25FELWDWWH4ZU6M4V2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2/action/storage_attestation","attest_author":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2/action/author_attestation","sign_citation":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2/action/citation_signature","submit_replication":"https://pith.science/pith/ZGJCF4QI25FELWDWWH4ZU6M4V2/action/replication_record"}},"created_at":"2026-07-05T04:09:58.184311+00:00","updated_at":"2026-07-05T04:09:58.184311+00:00"}