{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SHFQE5XZB3KTDGWJUXYP4K27JY","short_pith_number":"pith:SHFQE5XZ","schema_version":"1.0","canonical_sha256":"91cb0276f90ed5319ac9a5f0fe2b5f4e11c8667540b08ac93d8ec2e17d233524","source":{"kind":"arxiv","id":"2506.09784","version":1},"attestation_state":"computed","paper":{"title":"Accurate and efficient zero-shot 6D pose estimation with frozen foundation models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Caraffa, Davide Boscaini, Fabio Poiesi","submitted_at":"2025-06-11T14:23:38Z","abstract_excerpt":"Estimating the 6D pose of objects from RGBD data is a fundamental problem in computer vision, with applications in robotics and augmented reality. A key challenge is achieving generalization to novel objects that were not seen during training. Most existing approaches address this by scaling up training on synthetic data tailored to the task, a process that demands substantial computational resources. But is task-specific training really necessary for accurate and efficient 6D pose estimation of novel objects? To answer No!, we introduce FreeZeV2, the second generation of FreeZe: a training-fr"},"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":"2506.09784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T14:23:38Z","cross_cats_sorted":[],"title_canon_sha256":"ad9a8e939fbc56e895896458263468adc472d77e76fd329fdf1ea0116875437d","abstract_canon_sha256":"cf724585c0ffd19ded77f9c6213dc35a44042cf8b47e79b4662808b3fcdfd689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:56.892518Z","signature_b64":"5ELuTfKARdPCCqppUThU0vJcA8wgv/7wlsZobTt/9215uq/TQlWqjKpb91clowKPOpqGpAJ5l6yPmpNZCtqJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91cb0276f90ed5319ac9a5f0fe2b5f4e11c8667540b08ac93d8ec2e17d233524","last_reissued_at":"2026-07-05T11:19:56.892012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:56.892012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate and efficient zero-shot 6D pose estimation with frozen foundation models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Caraffa, Davide Boscaini, Fabio Poiesi","submitted_at":"2025-06-11T14:23:38Z","abstract_excerpt":"Estimating the 6D pose of objects from RGBD data is a fundamental problem in computer vision, with applications in robotics and augmented reality. A key challenge is achieving generalization to novel objects that were not seen during training. Most existing approaches address this by scaling up training on synthetic data tailored to the task, a process that demands substantial computational resources. But is task-specific training really necessary for accurate and efficient 6D pose estimation of novel objects? To answer No!, we introduce FreeZeV2, the second generation of FreeZe: a training-fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09784","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/2506.09784/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":"2506.09784","created_at":"2026-07-05T11:19:56.892076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09784v1","created_at":"2026-07-05T11:19:56.892076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09784","created_at":"2026-07-05T11:19:56.892076+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHFQE5XZB3KT","created_at":"2026-07-05T11:19:56.892076+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHFQE5XZB3KTDGWJ","created_at":"2026-07-05T11:19:56.892076+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHFQE5XZ","created_at":"2026-07-05T11:19:56.892076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20650","citing_title":"MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07023","citing_title":"Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY","json":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY.json","graph_json":"https://pith.science/api/pith-number/SHFQE5XZB3KTDGWJUXYP4K27JY/graph.json","events_json":"https://pith.science/api/pith-number/SHFQE5XZB3KTDGWJUXYP4K27JY/events.json","paper":"https://pith.science/paper/SHFQE5XZ"},"agent_actions":{"view_html":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY","download_json":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY.json","view_paper":"https://pith.science/paper/SHFQE5XZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09784&json=true","fetch_graph":"https://pith.science/api/pith-number/SHFQE5XZB3KTDGWJUXYP4K27JY/graph.json","fetch_events":"https://pith.science/api/pith-number/SHFQE5XZB3KTDGWJUXYP4K27JY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY/action/storage_attestation","attest_author":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY/action/author_attestation","sign_citation":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY/action/citation_signature","submit_replication":"https://pith.science/pith/SHFQE5XZB3KTDGWJUXYP4K27JY/action/replication_record"}},"created_at":"2026-07-05T11:19:56.892076+00:00","updated_at":"2026-07-05T11:19:56.892076+00:00"}