{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5MN2H33B7PSMYSBWSH6GNQOX2J","short_pith_number":"pith:5MN2H33B","schema_version":"1.0","canonical_sha256":"eb1ba3ef61fbe4cc483691fc66c1d7d27cdf94bec218a5e5e2447cceadc413d1","source":{"kind":"arxiv","id":"2508.02157","version":1},"attestation_state":"computed","paper":{"title":"Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eddy Ilg, Tom Fischer, Xiaojie Zhang","submitted_at":"2025-08-04T07:57:39Z","abstract_excerpt":"Recognizing objects in images is a fundamental problem in computer vision. Although detecting objects in 2D images is common, many applications require determining their pose in 3D space. Traditional category-level methods rely on RGB-D inputs, which may not always be available, or employ two-stage approaches that use separate models and representations for detection and pose estimation. For the first time, we introduce a unified model that integrates detection and pose estimation into a single framework for RGB images by leveraging neural mesh models with learned features and multi-model RANS"},"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":"2508.02157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T07:57:39Z","cross_cats_sorted":[],"title_canon_sha256":"b3c9a858521d3083df66f5b06dc88bae0f98c7c519e1d78e0efa019125b4bad3","abstract_canon_sha256":"5323c18c419b7c2649685a279332640aba4cce4fa4c519892dba44c539a4e014"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:09.375049Z","signature_b64":"GB5x+4rkQn6R56O+8fA32bm6i3+RBZ77/nL/koVPzk26fkzSm5oq7AAkSJxscne+G47KzEK7AH81KkkuVG95Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb1ba3ef61fbe4cc483691fc66c1d7d27cdf94bec218a5e5e2447cceadc413d1","last_reissued_at":"2026-07-05T11:48:09.374565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:09.374565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eddy Ilg, Tom Fischer, Xiaojie Zhang","submitted_at":"2025-08-04T07:57:39Z","abstract_excerpt":"Recognizing objects in images is a fundamental problem in computer vision. Although detecting objects in 2D images is common, many applications require determining their pose in 3D space. Traditional category-level methods rely on RGB-D inputs, which may not always be available, or employ two-stage approaches that use separate models and representations for detection and pose estimation. For the first time, we introduce a unified model that integrates detection and pose estimation into a single framework for RGB images by leveraging neural mesh models with learned features and multi-model RANS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02157","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/2508.02157/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":"2508.02157","created_at":"2026-07-05T11:48:09.374632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02157v1","created_at":"2026-07-05T11:48:09.374632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02157","created_at":"2026-07-05T11:48:09.374632+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MN2H33B7PSM","created_at":"2026-07-05T11:48:09.374632+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MN2H33B7PSMYSBW","created_at":"2026-07-05T11:48:09.374632+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MN2H33B","created_at":"2026-07-05T11:48:09.374632+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/5MN2H33B7PSMYSBWSH6GNQOX2J","json":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J.json","graph_json":"https://pith.science/api/pith-number/5MN2H33B7PSMYSBWSH6GNQOX2J/graph.json","events_json":"https://pith.science/api/pith-number/5MN2H33B7PSMYSBWSH6GNQOX2J/events.json","paper":"https://pith.science/paper/5MN2H33B"},"agent_actions":{"view_html":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J","download_json":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J.json","view_paper":"https://pith.science/paper/5MN2H33B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02157&json=true","fetch_graph":"https://pith.science/api/pith-number/5MN2H33B7PSMYSBWSH6GNQOX2J/graph.json","fetch_events":"https://pith.science/api/pith-number/5MN2H33B7PSMYSBWSH6GNQOX2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J/action/storage_attestation","attest_author":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J/action/author_attestation","sign_citation":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J/action/citation_signature","submit_replication":"https://pith.science/pith/5MN2H33B7PSMYSBWSH6GNQOX2J/action/replication_record"}},"created_at":"2026-07-05T11:48:09.374632+00:00","updated_at":"2026-07-05T11:48:09.374632+00:00"}