{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QJEEW3QUOVJ2CCIAKNFYCGT5I2","short_pith_number":"pith:QJEEW3QU","schema_version":"1.0","canonical_sha256":"82484b6e147553a10900534b811a7d4680ef6938d7e470433862356b5976a2f5","source":{"kind":"arxiv","id":"1702.01105","version":2},"attestation_state":"computed","paper":{"title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir R. Zamir, Iro Armeni, Sasha Sax, Silvio Savarese","submitted_at":"2017-02-03T18:28:33Z","abstract_excerpt":"We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360{\\deg} equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal "},"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":"1702.01105","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-03T18:28:33Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3c878d6308de3cd24db78fcc64ac1c3cad1007cfb051dbc3d98f7b24111d5797","abstract_canon_sha256":"b07834207a0402acb2fd638bbc26b4d1011f71554f6dc96d4f32959a1500af73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:55.139989Z","signature_b64":"X4yZmoMJ6VrHhHpvFEmSLtl6bP5loY2Z7GDNpgRtAhP+sfCtenxr8rDMSlICcooW8A91Tnp6t7yIyvHkFhBxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82484b6e147553a10900534b811a7d4680ef6938d7e470433862356b5976a2f5","last_reissued_at":"2026-05-18T00:46:55.139449Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:55.139449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir R. Zamir, Iro Armeni, Sasha Sax, Silvio Savarese","submitted_at":"2017-02-03T18:28:33Z","abstract_excerpt":"We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360{\\deg} equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01105","kind":"arxiv","version":2},"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":"1702.01105","created_at":"2026-05-18T00:46:55.139549+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.01105v2","created_at":"2026-05-18T00:46:55.139549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01105","created_at":"2026-05-18T00:46:55.139549+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJEEW3QUOVJ2","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJEEW3QUOVJ2CCIA","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJEEW3QU","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":18,"sample":[{"citing_arxiv_id":"2604.22482","citing_title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26839","citing_title":"Ordinal Neural Collapse as a Representation Prior for Visual Navigation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30047","citing_title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02479","citing_title":"EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\\circ$","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12368","citing_title":"DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30047","citing_title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27745","citing_title":"Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27178","citing_title":"FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00631","citing_title":"Automatic reconstruction of fully volumetric 3D building models from point clouds","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04444","citing_title":"A review on deep learning techniques for 3D sensed data classification","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2212.02011","citing_title":"PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02098","citing_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20737","citing_title":"Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2601.07447","citing_title":"PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2603.18943","citing_title":"VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14615","citing_title":"CalibAnyView: Beyond Single-View Camera Calibration in the Wild","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13152","citing_title":"EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2109.08238","citing_title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02829","citing_title":"STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11520","citing_title":"PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splatting","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24311","citing_title":"BIMStruct3D: A Fully Automated Hybrid Learning Scan-to-BIM Pipeline with Integrated Topology Refinement","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23095","citing_title":"INSIGHT: Indoor Scene Intelligence from Geometric-Semantic Hierarchy Transfer for Public~Safety","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22482","citing_title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02098","citing_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2","json":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2.json","graph_json":"https://pith.science/api/pith-number/QJEEW3QUOVJ2CCIAKNFYCGT5I2/graph.json","events_json":"https://pith.science/api/pith-number/QJEEW3QUOVJ2CCIAKNFYCGT5I2/events.json","paper":"https://pith.science/paper/QJEEW3QU"},"agent_actions":{"view_html":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2","download_json":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2.json","view_paper":"https://pith.science/paper/QJEEW3QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.01105&json=true","fetch_graph":"https://pith.science/api/pith-number/QJEEW3QUOVJ2CCIAKNFYCGT5I2/graph.json","fetch_events":"https://pith.science/api/pith-number/QJEEW3QUOVJ2CCIAKNFYCGT5I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2/action/storage_attestation","attest_author":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2/action/author_attestation","sign_citation":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2/action/citation_signature","submit_replication":"https://pith.science/pith/QJEEW3QUOVJ2CCIAKNFYCGT5I2/action/replication_record"}},"created_at":"2026-05-18T00:46:55.139549+00:00","updated_at":"2026-05-18T00:46:55.139549+00:00"}