{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DIB2RC2RS2JRE5GW55FDGK6J3U","short_pith_number":"pith:DIB2RC2R","schema_version":"1.0","canonical_sha256":"1a03a88b5196931274d6ef4a332bc9dd2cd91e6f4a4ead288eb3965e4bebdc96","source":{"kind":"arxiv","id":"2309.11986","version":1},"attestation_state":"computed","paper":{"title":"ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Haberger, Jean-Baptiste Weibel, Markus Vincze, Philipp Ausserlechner, Stefan Thalhammer","submitted_at":"2023-09-21T11:53:01Z","abstract_excerpt":"As robotic systems increasingly encounter complex and unconstrained real-world scenarios, there is a demand to recognize diverse objects. The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore do not generalize to unseen objects. Recent novel object pose estimation methods are solving this issue using task-specific fine-tuned CNNs for deep template matching. This adaptation for pose estimation still requires expensive data rendering and training procedures. MegaPose for example is trained on a dataset consisting of two million images showing 20,00"},"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":"2309.11986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-21T11:53:01Z","cross_cats_sorted":[],"title_canon_sha256":"606a45270cf57546828b3e84da01d00600d34c116e5e2a23f922d711bbdb0342","abstract_canon_sha256":"6ff847b5ef2118bdb80d6cd3ca8525fa652f1397892e67c7a135190cd82b0af5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:57.350717Z","signature_b64":"kXRZoh6nRGjRwZXy7hkMlFcU5s2QGOPNUedSFNLjD6YNSFKRWwDoxKHIGplRhVCcqYrJp40FikD0a9hzgsufBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a03a88b5196931274d6ef4a332bc9dd2cd91e6f4a4ead288eb3965e4bebdc96","last_reissued_at":"2026-07-05T06:52:57.350199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:57.350199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Haberger, Jean-Baptiste Weibel, Markus Vincze, Philipp Ausserlechner, Stefan Thalhammer","submitted_at":"2023-09-21T11:53:01Z","abstract_excerpt":"As robotic systems increasingly encounter complex and unconstrained real-world scenarios, there is a demand to recognize diverse objects. The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore do not generalize to unseen objects. Recent novel object pose estimation methods are solving this issue using task-specific fine-tuned CNNs for deep template matching. This adaptation for pose estimation still requires expensive data rendering and training procedures. MegaPose for example is trained on a dataset consisting of two million images showing 20,00"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11986","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/2309.11986/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":"2309.11986","created_at":"2026-07-05T06:52:57.350262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11986v1","created_at":"2026-07-05T06:52:57.350262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11986","created_at":"2026-07-05T06:52:57.350262+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIB2RC2RS2JR","created_at":"2026-07-05T06:52:57.350262+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIB2RC2RS2JRE5GW","created_at":"2026-07-05T06:52:57.350262+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIB2RC2R","created_at":"2026-07-05T06:52:57.350262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01004","citing_title":"ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U","json":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U.json","graph_json":"https://pith.science/api/pith-number/DIB2RC2RS2JRE5GW55FDGK6J3U/graph.json","events_json":"https://pith.science/api/pith-number/DIB2RC2RS2JRE5GW55FDGK6J3U/events.json","paper":"https://pith.science/paper/DIB2RC2R"},"agent_actions":{"view_html":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U","download_json":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U.json","view_paper":"https://pith.science/paper/DIB2RC2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11986&json=true","fetch_graph":"https://pith.science/api/pith-number/DIB2RC2RS2JRE5GW55FDGK6J3U/graph.json","fetch_events":"https://pith.science/api/pith-number/DIB2RC2RS2JRE5GW55FDGK6J3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U/action/storage_attestation","attest_author":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U/action/author_attestation","sign_citation":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U/action/citation_signature","submit_replication":"https://pith.science/pith/DIB2RC2RS2JRE5GW55FDGK6J3U/action/replication_record"}},"created_at":"2026-07-05T06:52:57.350262+00:00","updated_at":"2026-07-05T06:52:57.350262+00:00"}