{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K6ET7QN5RJNACLFDRUDSELEFTC","short_pith_number":"pith:K6ET7QN5","schema_version":"1.0","canonical_sha256":"57893fc1bd8a5a012ca38d07222c85989434d393965966dcfaca2b0c07fbf3d6","source":{"kind":"arxiv","id":"2411.16668","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Features for Zero-Shot 6DoF Object Pose Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernd Von Gimborn, Markus Vincze, Philipp Ausserlechner, Stefan Thalhammer","submitted_at":"2024-11-25T18:53:56Z","abstract_excerpt":"Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that are effectively general-purpose feature extractors. The characteristics exhibited by these VFMs vary depending on the training data, network architecture, and training paradigm. The prevailing choice in this field are self-supervised Vision Transformers (ViT). This study assesses the influence of Latent Diffusion Model (LDM) backbones on zero-shot pose esti"},"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":"2411.16668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"1a6e4f26baaa9eccaebc2b73b4e2ab5c79230c59dfc937bf8214ebfa3dedefe0","abstract_canon_sha256":"42bfe39b18d19b7f2635555e7ae24354c0a9116d5f970062f9700da69b210430"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:12.566129Z","signature_b64":"iRvAJVMWbS/7Kypeb/VRT1yLChZGMya1kN6VFK0Cc3zEMoPjVAMvxwGw4/jJfmQ6Zw97gWkOqYzSjtD8ntbBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57893fc1bd8a5a012ca38d07222c85989434d393965966dcfaca2b0c07fbf3d6","last_reissued_at":"2026-07-05T09:40:12.565700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:12.565700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Features for Zero-Shot 6DoF Object Pose Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernd Von Gimborn, Markus Vincze, Philipp Ausserlechner, Stefan Thalhammer","submitted_at":"2024-11-25T18:53:56Z","abstract_excerpt":"Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that are effectively general-purpose feature extractors. The characteristics exhibited by these VFMs vary depending on the training data, network architecture, and training paradigm. The prevailing choice in this field are self-supervised Vision Transformers (ViT). This study assesses the influence of Latent Diffusion Model (LDM) backbones on zero-shot pose esti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16668","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/2411.16668/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":"2411.16668","created_at":"2026-07-05T09:40:12.565763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16668v1","created_at":"2026-07-05T09:40:12.565763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16668","created_at":"2026-07-05T09:40:12.565763+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6ET7QN5RJNA","created_at":"2026-07-05T09:40:12.565763+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6ET7QN5RJNACLFD","created_at":"2026-07-05T09:40:12.565763+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6ET7QN5","created_at":"2026-07-05T09:40:12.565763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC","json":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC.json","graph_json":"https://pith.science/api/pith-number/K6ET7QN5RJNACLFDRUDSELEFTC/graph.json","events_json":"https://pith.science/api/pith-number/K6ET7QN5RJNACLFDRUDSELEFTC/events.json","paper":"https://pith.science/paper/K6ET7QN5"},"agent_actions":{"view_html":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC","download_json":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC.json","view_paper":"https://pith.science/paper/K6ET7QN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16668&json=true","fetch_graph":"https://pith.science/api/pith-number/K6ET7QN5RJNACLFDRUDSELEFTC/graph.json","fetch_events":"https://pith.science/api/pith-number/K6ET7QN5RJNACLFDRUDSELEFTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC/action/storage_attestation","attest_author":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC/action/author_attestation","sign_citation":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC/action/citation_signature","submit_replication":"https://pith.science/pith/K6ET7QN5RJNACLFDRUDSELEFTC/action/replication_record"}},"created_at":"2026-07-05T09:40:12.565763+00:00","updated_at":"2026-07-05T09:40:12.565763+00:00"}