{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EAQBJOKBVBV553PD7PNS2QWYSX","short_pith_number":"pith:EAQBJOKB","schema_version":"1.0","canonical_sha256":"202014b941a86bdeede3fbdb2d42d895dba68a8283022d803710392b35d7ba9d","source":{"kind":"arxiv","id":"2011.00359","version":1},"attestation_state":"computed","paper":{"title":"TartanVO: A Generalizable Learning-based VO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Sebastian Scherer, Wenshan Wang, Yaoyu Hu","submitted_at":"2020-10-31T20:49:33Z","abstract_excerpt":"We present the first learning-based visual odometry (VO) model, which generalizes to multiple datasets and real-world scenarios and outperforms geometry-based methods in challenging scenes. We achieve this by leveraging the SLAM dataset TartanAir, which provides a large amount of diverse synthetic data in challenging environments. Furthermore, to make our VO model generalize across datasets, we propose an up-to-scale loss function and incorporate the camera intrinsic parameters into the model. Experiments show that a single model, TartanVO, trained only on synthetic data, without any finetunin"},"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":"2011.00359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-31T20:49:33Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"557320d8632398502027a48ee4cfc8aa0090efd6613fc6e63de9b234ae98c19d","abstract_canon_sha256":"71675bb483fe84f079435818f69b5b1497a39da1713bbcd16f7d19e117802a84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:15.388566Z","signature_b64":"orXtO0qm8iUT09Izqs/X4VQaKDHPRFREO6+VJJ21jG4w/S/f+prIkzIyw+pzmYv5gJHPAIDrEPT7FgvZQWJLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"202014b941a86bdeede3fbdb2d42d895dba68a8283022d803710392b35d7ba9d","last_reissued_at":"2026-07-05T01:48:15.388134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:15.388134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TartanVO: A Generalizable Learning-based VO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Sebastian Scherer, Wenshan Wang, Yaoyu Hu","submitted_at":"2020-10-31T20:49:33Z","abstract_excerpt":"We present the first learning-based visual odometry (VO) model, which generalizes to multiple datasets and real-world scenarios and outperforms geometry-based methods in challenging scenes. We achieve this by leveraging the SLAM dataset TartanAir, which provides a large amount of diverse synthetic data in challenging environments. Furthermore, to make our VO model generalize across datasets, we propose an up-to-scale loss function and incorporate the camera intrinsic parameters into the model. Experiments show that a single model, TartanVO, trained only on synthetic data, without any finetunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00359","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/2011.00359/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":"2011.00359","created_at":"2026-07-05T01:48:15.388199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.00359v1","created_at":"2026-07-05T01:48:15.388199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00359","created_at":"2026-07-05T01:48:15.388199+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAQBJOKBVBV5","created_at":"2026-07-05T01:48:15.388199+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAQBJOKBVBV553PD","created_at":"2026-07-05T01:48:15.388199+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAQBJOKB","created_at":"2026-07-05T01:48:15.388199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22851","citing_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX","json":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX.json","graph_json":"https://pith.science/api/pith-number/EAQBJOKBVBV553PD7PNS2QWYSX/graph.json","events_json":"https://pith.science/api/pith-number/EAQBJOKBVBV553PD7PNS2QWYSX/events.json","paper":"https://pith.science/paper/EAQBJOKB"},"agent_actions":{"view_html":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX","download_json":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX.json","view_paper":"https://pith.science/paper/EAQBJOKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.00359&json=true","fetch_graph":"https://pith.science/api/pith-number/EAQBJOKBVBV553PD7PNS2QWYSX/graph.json","fetch_events":"https://pith.science/api/pith-number/EAQBJOKBVBV553PD7PNS2QWYSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX/action/storage_attestation","attest_author":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX/action/author_attestation","sign_citation":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX/action/citation_signature","submit_replication":"https://pith.science/pith/EAQBJOKBVBV553PD7PNS2QWYSX/action/replication_record"}},"created_at":"2026-07-05T01:48:15.388199+00:00","updated_at":"2026-07-05T01:48:15.388199+00:00"}