{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ICLJZT72OHPLK3DJELMPS3LQDZ","short_pith_number":"pith:ICLJZT72","schema_version":"1.0","canonical_sha256":"40969ccffa71deb56c6922d8f96d701e70591b398b7d62bec8835ed30e96e37d","source":{"kind":"arxiv","id":"2607.06555","version":1},"attestation_state":"computed","paper":{"title":"ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David B. Lindell, Felix Taubner, Kiriakos N. Kutulakos, Pooja Ravi, Ruihang Zhang","submitted_at":"2026-07-07T17:56:07Z","abstract_excerpt":"Tracking the six-degree-of-freedom (6-DoF) pose of objects and surfaces from monocular video is a long-standing problem in computer vision. To tackle this problem, existing methods require inputs beyond the video itself-such as 3D models, depth maps, object masks, or task-specific learned features-and they struggle with textureless, transparent, reflective, or deformable surfaces. Here, we introduce ProxyPose, which recasts 6-DoF pose tracking as video-to-video translation. Given only a video and a single marked pixel in the first frame, a fine-tuned video diffusion model translates the input "},"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":false},"canonical_record":{"source":{"id":"2607.06555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T17:56:07Z","cross_cats_sorted":[],"title_canon_sha256":"e4a8e085eb184ae1f4f7c2efcb7da0dab272777dea3b29de2181f2eb856403f0","abstract_canon_sha256":"40e6f4678d5ad5a29b53d84d7e7484e0b174bdccc50bc22e6b22b625cd866c44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:29.811569Z","signature_b64":"Uuu4Cs8LXrqZrQoWo6PbdQnJ7L9Tuqt+nvjoYD+iqTwuVuJ100ypXD9pH597OnFnz6ACFdFOYOHy/Q/OTbZNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40969ccffa71deb56c6922d8f96d701e70591b398b7d62bec8835ed30e96e37d","last_reissued_at":"2026-07-08T01:19:29.811114Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:29.811114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David B. Lindell, Felix Taubner, Kiriakos N. Kutulakos, Pooja Ravi, Ruihang Zhang","submitted_at":"2026-07-07T17:56:07Z","abstract_excerpt":"Tracking the six-degree-of-freedom (6-DoF) pose of objects and surfaces from monocular video is a long-standing problem in computer vision. To tackle this problem, existing methods require inputs beyond the video itself-such as 3D models, depth maps, object masks, or task-specific learned features-and they struggle with textureless, transparent, reflective, or deformable surfaces. Here, we introduce ProxyPose, which recasts 6-DoF pose tracking as video-to-video translation. Given only a video and a single marked pixel in the first frame, a fine-tuned video diffusion model translates the input "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06555","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.06555/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2607.06555","created_at":"2026-07-08T01:19:29.811178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06555v1","created_at":"2026-07-08T01:19:29.811178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06555","created_at":"2026-07-08T01:19:29.811178+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICLJZT72OHPL","created_at":"2026-07-08T01:19:29.811178+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICLJZT72OHPLK3DJ","created_at":"2026-07-08T01:19:29.811178+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICLJZT72","created_at":"2026-07-08T01:19:29.811178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07045","citing_title":"C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ","json":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ.json","graph_json":"https://pith.science/api/pith-number/ICLJZT72OHPLK3DJELMPS3LQDZ/graph.json","events_json":"https://pith.science/api/pith-number/ICLJZT72OHPLK3DJELMPS3LQDZ/events.json","paper":"https://pith.science/paper/ICLJZT72"},"agent_actions":{"view_html":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ","download_json":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ.json","view_paper":"https://pith.science/paper/ICLJZT72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06555&json=true","fetch_graph":"https://pith.science/api/pith-number/ICLJZT72OHPLK3DJELMPS3LQDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ICLJZT72OHPLK3DJELMPS3LQDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ/action/storage_attestation","attest_author":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ/action/author_attestation","sign_citation":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ/action/citation_signature","submit_replication":"https://pith.science/pith/ICLJZT72OHPLK3DJELMPS3LQDZ/action/replication_record"}},"created_at":"2026-07-08T01:19:29.811178+00:00","updated_at":"2026-07-08T01:19:29.811178+00:00"}