{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y3D33KXKMQJS2JSA3BSX6HB7KO","short_pith_number":"pith:Y3D33KXK","canonical_record":{"source":{"id":"2508.10934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T18:39:13Z","cross_cats_sorted":["cs.GR","cs.RO","eess.IV"],"title_canon_sha256":"5730616afc9835f41e55da11e13ce2885ddedee54ac1fafb57961333354dc3fd","abstract_canon_sha256":"c2ca1a658b07a02ce839784c279f8b386eef46e4ef17c13db9fd88f30e407d66"},"schema_version":"1.0"},"canonical_sha256":"c6c7bdaaea64132d2640d8657f1c3f539091f4f0ee4485b353e223441288fd3d","source":{"kind":"arxiv","id":"2508.10934","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10934","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10934v1","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10934","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"Y3D33KXKMQJS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y3D33KXKMQJS2JSA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y3D33KXK","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y3D33KXKMQJS2JSA3BSX6HB7KO","target":"record","payload":{"canonical_record":{"source":{"id":"2508.10934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T18:39:13Z","cross_cats_sorted":["cs.GR","cs.RO","eess.IV"],"title_canon_sha256":"5730616afc9835f41e55da11e13ce2885ddedee54ac1fafb57961333354dc3fd","abstract_canon_sha256":"c2ca1a658b07a02ce839784c279f8b386eef46e4ef17c13db9fd88f30e407d66"},"schema_version":"1.0"},"canonical_sha256":"c6c7bdaaea64132d2640d8657f1c3f539091f4f0ee4485b353e223441288fd3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.269130Z","signature_b64":"tFveF/z+jsAdx2ko3+4kivss2in6M4ozGPnRK30oxUjTB1wpZMhhSrm586fvaPNGwveLOQNmieREfAqdYRYmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6c7bdaaea64132d2640d8657f1c3f539091f4f0ee4485b353e223441288fd3d","last_reissued_at":"2026-05-17T23:38:47.268433Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.268433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.10934","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJkITM4s76QcZPyJNN+ZkA2wh4ZNVMYdKI94QoZoJe8m7HjDPO+qlhxL1BEY0R2mjiD0The0bLQDOuKUEma7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:53:14.028126Z"},"content_sha256":"a66e095e87935403df79245589b7e7c791c5de70ce2614c53a0756265b056d84","schema_version":"1.0","event_id":"sha256:a66e095e87935403df79245589b7e7c791c5de70ce2614c53a0756265b056d84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y3D33KXKMQJS2JSA3BSX6HB7KO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViPE: Video Pose Engine for 3D Geometric Perception","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"ViPE estimates camera poses and near-metric depth maps from any raw video without calibration.","cross_cats":["cs.GR","cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aleksandr Korovko, Chen-Hsuan Lin, Dmitry Slepichev, Hesam Rabeti, Huan Ling, Jiahui Huang, Jiawei Ren, Joydeep Biswas, Jun Gao, Kevin Xie, Laura Leal-Taixe, Qunjie Zhou, Sanja Fidler, Tianchang Shen, Xuanchi Ren","submitted_at":"2025-08-12T18:39:13Z","abstract_excerpt":"Accurate 3D geometric perception is an important prerequisite for a wide range of spatial AI systems. While state-of-the-art methods depend on large-scale training data, acquiring consistent and precise 3D annotations from in-the-wild videos remains a key challenge. In this work, we introduce ViPE, a handy and versatile video processing engine designed to bridge this gap. ViPE efficiently estimates camera intrinsics, camera motion, and dense, near-metric depth maps from unconstrained raw videos. It is robust to diverse scenarios, including dynamic selfie videos, cinematic shots, or dashcams, a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ViPE outperforms existing uncalibrated pose estimation baselines by 18%/50% on TUM/KITTI sequences and annotates approximately 96M frames with accurate camera poses and dense depth maps.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the engine produces reliable near-metric depth and accurate poses on diverse in-the-wild videos without per-video calibration or ground-truth supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ViPE estimates camera poses and near-metric depth maps from any raw video without calibration.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"61c187d4b97a8818f47918556c555791d95e0d9494de57e3f09883d9dd7864f2"},"source":{"id":"2508.10934","kind":"arxiv","version":1},"verdict":{"id":"42b6ed31-6f02-424b-bf91-8113f0e6d7f6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T16:36:23.572987Z","strongest_claim":"ViPE outperforms existing uncalibrated pose estimation baselines by 18%/50% on TUM/KITTI sequences and annotates approximately 96M frames with accurate camera poses and dense depth maps.","one_line_summary":"ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the engine produces reliable near-metric depth and accurate poses on diverse in-the-wild videos without per-video calibration or ground-truth supervision.","pith_extraction_headline":"ViPE estimates camera poses and near-metric depth maps from any raw video without calibration."},"references":{"count":91,"sample":[{"doi":"","year":2025,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","ref_index":1,"cited_arxiv_id":"2501.03575","is_internal_anchor":true},{"doi":"","year":2025,"title":"Cosmos-transfer1: Conditional world generation with adaptive multimodal control","work_id":"f6758fe8-a1a6-4b00-9094-edba697f4c67","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"L4P: Low-level 4D vision perception unified","work_id":"bd61ab0e-c22e-42a4-98c2-c3d9d91f1b5c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","work_id":"0ce910be-ca1c-44c7-b7b1-c5353759d85e","ref_index":4,"cited_arxiv_id":"2111.08897","is_internal_anchor":true},{"doi":"","year":2024,"title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","work_id":"0b67883b-1901-45f1-9d58-1ef7a928df23","ref_index":5,"cited_arxiv_id":"2410.02073","is_internal_anchor":true}],"resolved_work":91,"snapshot_sha256":"74eaf682a12148ca8b703638049077152f95852d79728d5d327bfa59603314bc","internal_anchors":9},"formal_canon":{"evidence_count":1,"snapshot_sha256":"18b533f88823abe8d9070541caf2fe0b151148bead9d4628fbb804db8165c227"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"42b6ed31-6f02-424b-bf91-8113f0e6d7f6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHb5/4dEhIZRY34mKWpHfBVpw5NSiHkF1HC8QMAl3db/AXeZSASSWobstfyQ+hKxSX9xzkV+8bLBh47AjwuNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:53:14.028711Z"},"content_sha256":"0705f00ca2ee31fe50f9694e8a0b428dfb2435838aa378bf0e740195e3cee3c1","schema_version":"1.0","event_id":"sha256:0705f00ca2ee31fe50f9694e8a0b428dfb2435838aa378bf0e740195e3cee3c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/bundle.json","state_url":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T18:53:14Z","links":{"resolver":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO","bundle":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/bundle.json","state":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y3D33KXKMQJS2JSA3BSX6HB7KO","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":"c2ca1a658b07a02ce839784c279f8b386eef46e4ef17c13db9fd88f30e407d66","cross_cats_sorted":["cs.GR","cs.RO","eess.IV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T18:39:13Z","title_canon_sha256":"5730616afc9835f41e55da11e13ce2885ddedee54ac1fafb57961333354dc3fd"},"schema_version":"1.0","source":{"id":"2508.10934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10934","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10934v1","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10934","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"Y3D33KXKMQJS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y3D33KXKMQJS2JSA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y3D33KXK","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0705f00ca2ee31fe50f9694e8a0b428dfb2435838aa378bf0e740195e3cee3c1","target":"graph","created_at":"2026-05-17T23:38:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ViPE outperforms existing uncalibrated pose estimation baselines by 18%/50% on TUM/KITTI sequences and annotates approximately 96M frames with accurate camera poses and dense depth maps."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the engine produces reliable near-metric depth and accurate poses on diverse in-the-wild videos without per-video calibration or ground-truth supervision."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ViPE estimates camera poses and near-metric depth maps from any raw video without calibration."}],"snapshot_sha256":"61c187d4b97a8818f47918556c555791d95e0d9494de57e3f09883d9dd7864f2"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"18b533f88823abe8d9070541caf2fe0b151148bead9d4628fbb804db8165c227"},"paper":{"abstract_excerpt":"Accurate 3D geometric perception is an important prerequisite for a wide range of spatial AI systems. While state-of-the-art methods depend on large-scale training data, acquiring consistent and precise 3D annotations from in-the-wild videos remains a key challenge. In this work, we introduce ViPE, a handy and versatile video processing engine designed to bridge this gap. ViPE efficiently estimates camera intrinsics, camera motion, and dense, near-metric depth maps from unconstrained raw videos. It is robust to diverse scenarios, including dynamic selfie videos, cinematic shots, or dashcams, a","authors_text":"Aleksandr Korovko, Chen-Hsuan Lin, Dmitry Slepichev, Hesam Rabeti, Huan Ling, Jiahui Huang, Jiawei Ren, Joydeep Biswas, Jun Gao, Kevin Xie, Laura Leal-Taixe, Qunjie Zhou, Sanja Fidler, Tianchang Shen, Xuanchi Ren","cross_cats":["cs.GR","cs.RO","eess.IV"],"headline":"ViPE estimates camera poses and near-metric depth maps from any raw video without calibration.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T18:39:13Z","title":"ViPE: Video Pose Engine for 3D Geometric Perception"},"references":{"count":91,"internal_anchors":9,"resolved_work":91,"sample":[{"cited_arxiv_id":"2501.03575","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Cosmos-transfer1: Conditional world generation with adaptive multimodal control","work_id":"f6758fe8-a1a6-4b00-9094-edba697f4c67","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"L4P: Low-level 4D vision perception unified","work_id":"bd61ab0e-c22e-42a4-98c2-c3d9d91f1b5c","year":null},{"cited_arxiv_id":"2111.08897","doi":"","is_internal_anchor":true,"ref_index":4,"title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","work_id":"0ce910be-ca1c-44c7-b7b1-c5353759d85e","year":2021},{"cited_arxiv_id":"2410.02073","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","work_id":"0b67883b-1901-45f1-9d58-1ef7a928df23","year":2024}],"snapshot_sha256":"74eaf682a12148ca8b703638049077152f95852d79728d5d327bfa59603314bc"},"source":{"id":"2508.10934","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T16:36:23.572987Z","id":"42b6ed31-6f02-424b-bf91-8113f0e6d7f6","model_set":{"reader":"grok-4.3"},"one_line_summary":"ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ViPE estimates camera poses and near-metric depth maps from any raw video without calibration.","strongest_claim":"ViPE outperforms existing uncalibrated pose estimation baselines by 18%/50% on TUM/KITTI sequences and annotates approximately 96M frames with accurate camera poses and dense depth maps.","weakest_assumption":"That the engine produces reliable near-metric depth and accurate poses on diverse in-the-wild videos without per-video calibration or ground-truth supervision."}},"verdict_id":"42b6ed31-6f02-424b-bf91-8113f0e6d7f6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a66e095e87935403df79245589b7e7c791c5de70ce2614c53a0756265b056d84","target":"record","created_at":"2026-05-17T23:38:47Z","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":"c2ca1a658b07a02ce839784c279f8b386eef46e4ef17c13db9fd88f30e407d66","cross_cats_sorted":["cs.GR","cs.RO","eess.IV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T18:39:13Z","title_canon_sha256":"5730616afc9835f41e55da11e13ce2885ddedee54ac1fafb57961333354dc3fd"},"schema_version":"1.0","source":{"id":"2508.10934","kind":"arxiv","version":1}},"canonical_sha256":"c6c7bdaaea64132d2640d8657f1c3f539091f4f0ee4485b353e223441288fd3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6c7bdaaea64132d2640d8657f1c3f539091f4f0ee4485b353e223441288fd3d","first_computed_at":"2026-05-17T23:38:47.268433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.268433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tFveF/z+jsAdx2ko3+4kivss2in6M4ozGPnRK30oxUjTB1wpZMhhSrm586fvaPNGwveLOQNmieREfAqdYRYmDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.269130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a66e095e87935403df79245589b7e7c791c5de70ce2614c53a0756265b056d84","sha256:0705f00ca2ee31fe50f9694e8a0b428dfb2435838aa378bf0e740195e3cee3c1"],"state_sha256":"9d11580489725fcfc009ae46d788f7d5ab382294949b0ba870e4d57864dba1b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClIWvTzhJlZc28LWMlR5IWSBWLb41dr6XgCcpFViM5xhCa7Bw0sadIoISD6ZnfccdIbrteOZwWUUMNTcawIYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:53:14.032982Z","bundle_sha256":"8dfc174d294ad119c0325f47169078180e22a8facdeddedd970b792b984d70ee"}}