{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UXKCP4VWA6JEBMADQ4S2ZXOBCZ","short_pith_number":"pith:UXKCP4VW","schema_version":"1.0","canonical_sha256":"a5d427f2b6079240b0038725acddc116698d8a0c5ccdf57e8e95d8585a3eaa94","source":{"kind":"arxiv","id":"2605.10525","version":4},"attestation_state":"computed","paper":{"title":"GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanrui Cheng, Junda Cheng, Longliang Liu, Wenjing Liao, Xin Yang, Yuecheng Liu, Yuzhou Wang","submitted_at":"2026-05-11T13:11:54Z","abstract_excerpt":"Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency-particularly under rotations or drastic view changes. To address this, we propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency. Distincti"},"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":true},"canonical_record":{"source":{"id":"2605.10525","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T13:11:54Z","cross_cats_sorted":[],"title_canon_sha256":"7592fd0883041cccfac7ae87ecfe2faf5bf6eea261a0b434693f3713b17860df","abstract_canon_sha256":"8e7515614090554cd7402014b3e86b06b86152eaa9f47610e396738a78608535"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:16.497732Z","signature_b64":"aC9kaS6gHpViXwSViUy1q7HwFgiTfGcoAvOsVtIxCJ48FXeOQ3KYY6r3fCT93ExI3rJ8cLYI81u7hpUUJvU/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d427f2b6079240b0038725acddc116698d8a0c5ccdf57e8e95d8585a3eaa94","last_reissued_at":"2026-05-20T01:05:16.497143Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:16.497143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanrui Cheng, Junda Cheng, Longliang Liu, Wenjing Liao, Xin Yang, Yuecheng Liu, Yuzhou Wang","submitted_at":"2026-05-11T13:11:54Z","abstract_excerpt":"Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency-particularly under rotations or drastic view changes. To address this, we propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency. Distincti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That predicting inter-frame camera poses and injecting the resulting geometric embeddings is a prerequisite for strict 3D consistency under rotations or drastic view changes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"80438595b31431519e9ea6dba5fdfcec63c4fc113798ed2fe9aa4c191b71c601"},"source":{"id":"2605.10525","kind":"arxiv","version":4},"verdict":{"id":"67b9e8b1-0d64-4492-8b1e-b1ea42ed182c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:24:42.864887Z","strongest_claim":"GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios.","one_line_summary":"GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That predicting inter-frame camera poses and injecting the resulting geometric embeddings is a prerequisite for strict 3D consistency under rotations or drastic view changes.","pith_extraction_headline":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10525/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:42:07.908786Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:17.869831Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:12:29.466117Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e541b2a2e5568f4f98af6b2ca3dc7af5ac45400cd5819c7fbb84046f6aacb765"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d92fc18f344a799a4924c04fa3abe32d116481688887298c9abf89a54530d1bb"},"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":"2605.10525","created_at":"2026-05-20T01:05:16.497238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10525v4","created_at":"2026-05-20T01:05:16.497238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10525","created_at":"2026-05-20T01:05:16.497238+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXKCP4VWA6JE","created_at":"2026-05-20T01:05:16.497238+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXKCP4VWA6JEBMAD","created_at":"2026-05-20T01:05:16.497238+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXKCP4VW","created_at":"2026-05-20T01:05:16.497238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ","json":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ.json","graph_json":"https://pith.science/api/pith-number/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/graph.json","events_json":"https://pith.science/api/pith-number/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/events.json","paper":"https://pith.science/paper/UXKCP4VW"},"agent_actions":{"view_html":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ","download_json":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ.json","view_paper":"https://pith.science/paper/UXKCP4VW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10525&json=true","fetch_graph":"https://pith.science/api/pith-number/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/action/storage_attestation","attest_author":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/action/author_attestation","sign_citation":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/action/citation_signature","submit_replication":"https://pith.science/pith/UXKCP4VWA6JEBMADQ4S2ZXOBCZ/action/replication_record"}},"created_at":"2026-05-20T01:05:16.497238+00:00","updated_at":"2026-05-20T01:05:16.497238+00:00"}