{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SFLSVBM6DWWYID2LHXTWJZOT22","short_pith_number":"pith:SFLSVBM6","schema_version":"1.0","canonical_sha256":"91572a859e1dad840f4b3de764e5d3d6a5a1a68de5e137919f7f3e6cde50b5af","source":{"kind":"arxiv","id":"2301.05871","version":2},"attestation_state":"computed","paper":{"title":"Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhui Zhao, Songchun Zhang","submitted_at":"2023-01-14T09:43:23Z","abstract_excerpt":"Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the motion of dynamic objects. In this paper, we propose a novel Dyna-Depthformer framework, which predicts scene depth and 3D motion field jointly and aggregates multi-frame information with transformer. Our contributions are two-fold. First, we leverage multi-view correlation through a series of self- and cross-attention layers in order to obtain enhanced depth "},"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":"2301.05871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-14T09:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"ecb932c0ded2b911787fbf6b91f98d139740a9650480e326511f0885fe9f4ddc","abstract_canon_sha256":"eaa565c9a6a3081c4aa7861bb7952957a88e242d391b40bde5e689f1c2d6906a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:25.563065Z","signature_b64":"NlQWZJVstoHPP+UCYswAoJBo0jwvb0NVzSXNRQ2/LU7GKW+uEZVjQnAmk4GDMuwYWp2e7UFu6dyOTo2nneciAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91572a859e1dad840f4b3de764e5d3d6a5a1a68de5e137919f7f3e6cde50b5af","last_reissued_at":"2026-07-05T05:52:25.562634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:25.562634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhui Zhao, Songchun Zhang","submitted_at":"2023-01-14T09:43:23Z","abstract_excerpt":"Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the motion of dynamic objects. In this paper, we propose a novel Dyna-Depthformer framework, which predicts scene depth and 3D motion field jointly and aggregates multi-frame information with transformer. Our contributions are two-fold. First, we leverage multi-view correlation through a series of self- and cross-attention layers in order to obtain enhanced depth "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05871","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/2301.05871/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":"2301.05871","created_at":"2026-07-05T05:52:25.562694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.05871v2","created_at":"2026-07-05T05:52:25.562694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05871","created_at":"2026-07-05T05:52:25.562694+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFLSVBM6DWWY","created_at":"2026-07-05T05:52:25.562694+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFLSVBM6DWWYID2L","created_at":"2026-07-05T05:52:25.562694+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFLSVBM6","created_at":"2026-07-05T05:52:25.562694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22","json":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22.json","graph_json":"https://pith.science/api/pith-number/SFLSVBM6DWWYID2LHXTWJZOT22/graph.json","events_json":"https://pith.science/api/pith-number/SFLSVBM6DWWYID2LHXTWJZOT22/events.json","paper":"https://pith.science/paper/SFLSVBM6"},"agent_actions":{"view_html":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22","download_json":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22.json","view_paper":"https://pith.science/paper/SFLSVBM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.05871&json=true","fetch_graph":"https://pith.science/api/pith-number/SFLSVBM6DWWYID2LHXTWJZOT22/graph.json","fetch_events":"https://pith.science/api/pith-number/SFLSVBM6DWWYID2LHXTWJZOT22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22/action/storage_attestation","attest_author":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22/action/author_attestation","sign_citation":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22/action/citation_signature","submit_replication":"https://pith.science/pith/SFLSVBM6DWWYID2LHXTWJZOT22/action/replication_record"}},"created_at":"2026-07-05T05:52:25.562694+00:00","updated_at":"2026-07-05T05:52:25.562694+00:00"}