{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NQ3LEHSTMQHE4VJJEUTRTKREVU","short_pith_number":"pith:NQ3LEHST","schema_version":"1.0","canonical_sha256":"6c36b21e53640e4e5529252719aa24ad385c5826024933ea6af2038544656485","source":{"kind":"arxiv","id":"2605.12774","version":1},"attestation_state":"computed","paper":{"title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"WildPose unifies monocular pose estimation to stay accurate in dynamic scenes without losing ground on static or low-motion ones.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iro Armeni, Jianhao Zheng, Liyuan Zhu, Zihan Zhu","submitted_at":"2026-05-12T21:39:44Z","abstract_excerpt":"Estimating camera pose in dynamic environments is a critical challenge, as most visual SLAM and SfM methods assume static scenes. While recent dynamic-aware methods exist, they are often not unified: semantic-based approaches are brittle, per-sequence optimization methods fail on short sequences, and other learned models may degrade on static-only scenes. We present WildPose, a unified monocular pose estimation framework that is robust in dynamic environments while maintaining state-of-the-art performance on static and low-ego-motion datasets. Our key insight is to connect two powerful paradig"},"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":"2605.12774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T21:39:44Z","cross_cats_sorted":[],"title_canon_sha256":"149945b0fa3bfd0a2bb7b2f0a9521d081cc018fbcd800f6af016594d4a33acc1","abstract_canon_sha256":"54694107e6b47bd6d198735f2a90e8a04f17a2274b3b82e63f241d6518540b04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:20.059502Z","signature_b64":"yzN8WPaenfkV27s83bd/XR4QwuoDx6tGo0u82h14YLsozWJVnLO+YlzLovhSXvk5AgHh8RtZ8+1Y2yKMc3NtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c36b21e53640e4e5529252719aa24ad385c5826024933ea6af2038544656485","last_reissued_at":"2026-05-18T03:09:20.058740Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:20.058740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"WildPose unifies monocular pose estimation to stay accurate in dynamic scenes without losing ground on static or low-motion ones.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iro Armeni, Jianhao Zheng, Liyuan Zhu, Zihan Zhu","submitted_at":"2026-05-12T21:39:44Z","abstract_excerpt":"Estimating camera pose in dynamic environments is a critical challenge, as most visual SLAM and SfM methods assume static scenes. While recent dynamic-aware methods exist, they are often not unified: semantic-based approaches are brittle, per-sequence optimization methods fail on short sequences, and other learned models may degrade on static-only scenes. We present WildPose, a unified monocular pose estimation framework that is robust in dynamic environments while maintaining state-of-the-art performance on static and low-ego-motion datasets. Our key insight is to connect two powerful paradig"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"WildPose consistently outperforms prior methods across dynamic (Wild-SLAM, Bonn), static (TUM, 7-Scenes), and low-ego-motion (Sintel) benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a frozen pre-trained MASt3R backbone supplies sufficiently rich and general 3D-aware features for both the update operator and motion mask detector to deliver unified robustness without scene-specific retraining or failure modes in unseen dynamics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"WildPose unifies monocular pose estimation to stay accurate in dynamic scenes without losing ground on static or low-motion ones.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d683c8c450de5c50dc77464a74bebc415c1282a52bcd2a56b2bb5de528fb6e9b"},"source":{"id":"2605.12774","kind":"arxiv","version":1},"verdict":{"id":"3e7d3a39-99a7-4144-96f7-1deb3704d861","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:34:19.048067Z","strongest_claim":"WildPose consistently outperforms prior methods across dynamic (Wild-SLAM, Bonn), static (TUM, 7-Scenes), and low-ego-motion (Sintel) benchmarks.","one_line_summary":"WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a frozen pre-trained MASt3R backbone supplies sufficiently rich and general 3D-aware features for both the update operator and motion mask detector to deliver unified robustness without scene-specific retraining or failure modes in unseen dynamics.","pith_extraction_headline":"WildPose unifies monocular pose estimation to stay accurate in dynamic scenes without losing ground on static or low-motion ones."},"references":{"count":72,"sample":[{"doi":"","year":2018,"title":"Fácil, Javier Civera, and José Neira","work_id":"490fd45e-a87c-4270-bc0b-b7b35baa0520","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"A naturalistic open source movie for optical flow evaluation","work_id":"d4c5c49b-f5f0-41bc-8b80-df8b660bc546","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Orb-slam3: An accu- rate open-source library for visual, visual–inertial, and mul- timap slam.IEEE transactions on robotics, 37(6):1874–1890,","work_id":"27d28ed6-c2e5-4fa0-bc3f-0edd27a4f2c0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Video depth anything: Consistent depth estimation for super-long videos","work_id":"79a25c43-dc22-412e-8807-555f77f0a128","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Back on track: Bundle adjustment for dynamic scene reconstruc- tion","work_id":"86b6761f-a7bf-4610-b5c8-68391da12516","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":72,"snapshot_sha256":"d0b4eb8eaeba7947de11331cc6a63b4b34dfbaf223ed5f056d5ca068b7b83726","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"64034ed3ff1e98c109ce95fc923ca54fe3280b5f6d2f79e9ad5a3a7bfa97283d"},"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":"2605.12774","created_at":"2026-05-18T03:09:20.058847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12774v1","created_at":"2026-05-18T03:09:20.058847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12774","created_at":"2026-05-18T03:09:20.058847+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQ3LEHSTMQHE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQ3LEHSTMQHE4VJJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQ3LEHST","created_at":"2026-05-18T12:33:37.589309+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/NQ3LEHSTMQHE4VJJEUTRTKREVU","json":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU.json","graph_json":"https://pith.science/api/pith-number/NQ3LEHSTMQHE4VJJEUTRTKREVU/graph.json","events_json":"https://pith.science/api/pith-number/NQ3LEHSTMQHE4VJJEUTRTKREVU/events.json","paper":"https://pith.science/paper/NQ3LEHST"},"agent_actions":{"view_html":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU","download_json":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU.json","view_paper":"https://pith.science/paper/NQ3LEHST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12774&json=true","fetch_graph":"https://pith.science/api/pith-number/NQ3LEHSTMQHE4VJJEUTRTKREVU/graph.json","fetch_events":"https://pith.science/api/pith-number/NQ3LEHSTMQHE4VJJEUTRTKREVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU/action/storage_attestation","attest_author":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU/action/author_attestation","sign_citation":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU/action/citation_signature","submit_replication":"https://pith.science/pith/NQ3LEHSTMQHE4VJJEUTRTKREVU/action/replication_record"}},"created_at":"2026-05-18T03:09:20.058847+00:00","updated_at":"2026-05-18T03:09:20.058847+00:00"}