{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SYRXEC6LWEB37BELTHPR6733ZW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"55d5ed19b730e064bbbcc96be260d13da5a9b595e524a54c36b084dd4b686846","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T02:30:46Z","title_canon_sha256":"8fe97654e168318725143412c93fc1e785bab49f9f34e1a4c784d090a26f12da"},"schema_version":"1.0","source":{"id":"2404.15506","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15506","created_at":"2026-07-05T09:56:35Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15506v4","created_at":"2026-07-05T09:56:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15506","created_at":"2026-07-05T09:56:35Z"},{"alias_kind":"pith_short_12","alias_value":"SYRXEC6LWEB3","created_at":"2026-07-05T09:56:35Z"},{"alias_kind":"pith_short_16","alias_value":"SYRXEC6LWEB37BEL","created_at":"2026-07-05T09:56:35Z"},{"alias_kind":"pith_short_8","alias_value":"SYRXEC6L","created_at":"2026-07-05T09:56:35Z"}],"graph_snapshots":[{"event_id":"sha256:f9fe5fd3fdca3207926afe783bf6a5568f557a5f31a32c81da34705012eb9aee","target":"graph","created_at":"2026-07-05T09:56:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.15506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically related and highly complimentary, they present distinct challenges. SoTA monocular depth methods achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. Meanwhile, SoTA normal estimation methods have limited zero-shot performance due to the lack of large-scale labeled data. To tackle these issues, we propose solutions for both m","authors_text":"Chi Zhang, Chunhua Shen, Gang Yu, Hao Chen, Kaixuan Wang, Mu Hu, Shaojie Shen, Wei Yin, Xiaoxiao Long, Zhipeng Cai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T02:30:46Z","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15506","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:470fc031056437e1d4edf2ad3a538b02428c42c9c2d5c4079a93436cdc6873e6","target":"record","created_at":"2026-07-05T09:56:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"55d5ed19b730e064bbbcc96be260d13da5a9b595e524a54c36b084dd4b686846","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T02:30:46Z","title_canon_sha256":"8fe97654e168318725143412c93fc1e785bab49f9f34e1a4c784d090a26f12da"},"schema_version":"1.0","source":{"id":"2404.15506","kind":"arxiv","version":4}},"canonical_sha256":"9623720bcbb103bf848b99df1f7f7bcd9096963e0a97cf83da682bb5596eccf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9623720bcbb103bf848b99df1f7f7bcd9096963e0a97cf83da682bb5596eccf6","first_computed_at":"2026-07-05T09:56:35.460370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:35.460370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PQTys9pTj6XSfX53dd6YNUvWCjmJG2yDOgZ0B34nQuNppaRJbrV39eqfPJTUWHzcoAjO3vAdpLlpux/Mv8+oBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:35.460873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15506","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:470fc031056437e1d4edf2ad3a538b02428c42c9c2d5c4079a93436cdc6873e6","sha256:f9fe5fd3fdca3207926afe783bf6a5568f557a5f31a32c81da34705012eb9aee"],"state_sha256":"85ba094fd39577a22bea9ca5c25cc6c8aa3316443e4486270ef3ae3bee3a0c70"}