{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y3D33KXKMQJS2JSA3BSX6HB7KO","short_pith_number":"pith:Y3D33KXK","schema_version":"1.0","canonical_sha256":"c6c7bdaaea64132d2640d8657f1c3f539091f4f0ee4485b353e223441288fd3d","source":{"kind":"arxiv","id":"2508.10934","version":1},"attestation_state":"computed","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"},"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":true,"formal_links_present":true},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.10934","created_at":"2026-05-17T23:38:47.268533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10934v1","created_at":"2026-05-17T23:38:47.268533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10934","created_at":"2026-05-17T23:38:47.268533+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3D33KXKMQJS","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3D33KXKMQJS2JSA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3D33KXK","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":21,"sample":[{"citing_arxiv_id":"2511.17792","citing_title":"Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26645","citing_title":"TTT3R: 3D Reconstruction as Test-Time Training","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10226","citing_title":"Latent Chain-of-Thought World Modeling for End-to-End Driving","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2602.19035","citing_title":"OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14614","citing_title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15178","citing_title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14615","citing_title":"CalibAnyView: Beyond Single-View Camera Calibration in the Wild","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12587","citing_title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12774","citing_title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26067","citing_title":"RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06051","citing_title":"RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11038","citing_title":"EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07348","citing_title":"MoRight: Motion Control Done Right","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08995","citing_title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14141","citing_title":"Geometric Context Transformer for Streaming 3D Reconstruction","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13793","citing_title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21776","citing_title":"Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO","json":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO.json","graph_json":"https://pith.science/api/pith-number/Y3D33KXKMQJS2JSA3BSX6HB7KO/graph.json","events_json":"https://pith.science/api/pith-number/Y3D33KXKMQJS2JSA3BSX6HB7KO/events.json","paper":"https://pith.science/paper/2508.10934"},"agent_actions":{"view_html":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO","download_json":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO.json","view_paper":"https://pith.science/paper/2508.10934","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10934&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3D33KXKMQJS2JSA3BSX6HB7KO/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3D33KXKMQJS2JSA3BSX6HB7KO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/action/storage_attestation","attest_author":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/action/author_attestation","sign_citation":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/action/citation_signature","submit_replication":"https://pith.science/pith/Y3D33KXKMQJS2JSA3BSX6HB7KO/action/replication_record"}},"created_at":"2026-05-17T23:38:47.268533+00:00","updated_at":"2026-05-17T23:38:47.268533+00:00"}