{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UYTWSXAMCIB2JTSJ2BTECIOWRP","short_pith_number":"pith:UYTWSXAM","schema_version":"1.0","canonical_sha256":"a627695c0c1203a4ce49d0664121d68bf2e2a978826b73cc3664691b66c05e65","source":{"kind":"arxiv","id":"1711.00199","version":3},"attestation_state":"computed","paper":{"title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dieter Fox, Tanner Schmidt, Venkatraman Narayanan, Yu Xiang","submitted_at":"2017-11-01T04:10:58Z","abstract_excerpt":"Estimating the 6D pose of known objects is important for robots to interact with the real world. The problem is challenging due to the variety of objects as well as the complexity of a scene caused by clutter and occlusions between objects. In this work, we introduce PoseCNN, a new Convolutional Neural Network for 6D object pose estimation. PoseCNN estimates the 3D translation of an object by localizing its center in the image and predicting its distance from the camera. The 3D rotation of the object is estimated by regressing to a quaternion representation. We also introduce a novel loss func"},"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":"1711.00199","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-01T04:10:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5270f03ed01a90e5b19fc65d501d33d65b174867c5adef0059b58a1e7ce4e2ba","abstract_canon_sha256":"ff7c267c608c10e2d3a6727f9d6f420ccb10c9e701691f73c2d3987065bb3a6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:54.280551Z","signature_b64":"jnBqQ1OKFrXBHbgcP0FoAsG0sZwF4DWhlXd0nkdVA9T6j/E8InNzf8vRm4NvD4BZMH1WViYGecCgTVBgsC4pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a627695c0c1203a4ce49d0664121d68bf2e2a978826b73cc3664691b66c05e65","last_reissued_at":"2026-05-18T00:14:54.279893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:54.279893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dieter Fox, Tanner Schmidt, Venkatraman Narayanan, Yu Xiang","submitted_at":"2017-11-01T04:10:58Z","abstract_excerpt":"Estimating the 6D pose of known objects is important for robots to interact with the real world. The problem is challenging due to the variety of objects as well as the complexity of a scene caused by clutter and occlusions between objects. In this work, we introduce PoseCNN, a new Convolutional Neural Network for 6D object pose estimation. PoseCNN estimates the 3D translation of an object by localizing its center in the image and predicting its distance from the camera. The 3D rotation of the object is estimated by regressing to a quaternion representation. We also introduce a novel loss func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00199","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.00199","created_at":"2026-05-18T00:14:54.279995+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00199v3","created_at":"2026-05-18T00:14:54.279995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00199","created_at":"2026-05-18T00:14:54.279995+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYTWSXAMCIB2","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYTWSXAMCIB2JTSJ","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYTWSXAM","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2503.23171","citing_title":"Deep Visual Servoing of an Aerial Robot Using Keypoint Feature Extraction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17865","citing_title":"Imaging Hidden Objects with Consumer LiDAR via Motion Induced Sampling","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17033","citing_title":"Generalizable and Actionable Parts Pose Estimation with Symmetry Annotation-Free Learning Strategy","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13998","citing_title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06565","citing_title":"GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2403.09227","citing_title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20150","citing_title":"Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28045","citing_title":"Event6D: Event-based Novel Object 6D Pose Tracking","ref_index":141,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13233","citing_title":"Doppler Prompting for Stable mmWave-based Human Pose Estimation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04050","citing_title":"TORA: Topological Representation Alignment for 3D Shape Assembly","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11756","citing_title":"Focusable Monocular Depth Estimation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20650","citing_title":"MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10415","citing_title":"Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09100","citing_title":"Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07413","citing_title":"FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16954","citing_title":"TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02708","citing_title":"Temporally Consistent Object 6D Pose Estimation for Robot Control","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP","json":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP.json","graph_json":"https://pith.science/api/pith-number/UYTWSXAMCIB2JTSJ2BTECIOWRP/graph.json","events_json":"https://pith.science/api/pith-number/UYTWSXAMCIB2JTSJ2BTECIOWRP/events.json","paper":"https://pith.science/paper/UYTWSXAM"},"agent_actions":{"view_html":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP","download_json":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP.json","view_paper":"https://pith.science/paper/UYTWSXAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00199&json=true","fetch_graph":"https://pith.science/api/pith-number/UYTWSXAMCIB2JTSJ2BTECIOWRP/graph.json","fetch_events":"https://pith.science/api/pith-number/UYTWSXAMCIB2JTSJ2BTECIOWRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP/action/storage_attestation","attest_author":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP/action/author_attestation","sign_citation":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP/action/citation_signature","submit_replication":"https://pith.science/pith/UYTWSXAMCIB2JTSJ2BTECIOWRP/action/replication_record"}},"created_at":"2026-05-18T00:14:54.279995+00:00","updated_at":"2026-05-18T00:14:54.279995+00:00"}