{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4G4MPFS7H5ORGDYXB2SODVGVPQ","short_pith_number":"pith:4G4MPFS7","schema_version":"1.0","canonical_sha256":"e1b8c7965f3f5d130f170ea4e1d4d57c14ee3c47593d9a33316e95e814000fc6","source":{"kind":"arxiv","id":"1806.05361","version":1},"attestation_state":"computed","paper":{"title":"View-volume Network for Semantic Scene Completion from a Single Depth Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xin Tong, Yu-Xiao Guo","submitted_at":"2018-06-14T04:42:05Z","abstract_excerpt":"We introduce a View-Volume convolutional neural network (VVNet) for inferring the occupancy and semantic labels of a volumetric 3D scene from a single depth image. The VVNet concatenates a 2D view CNN and a 3D volume CNN with a differentiable projection layer. Given a single RGBD image, our method extracts the detailed geometric features from the input depth image with a 2D view CNN and then projects the features into a 3D volume according to the input depth map via a projection layer. After that, we learn the 3D context information of the scene with a 3D volume CNN for computing the result vo"},"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":"1806.05361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-14T04:42:05Z","cross_cats_sorted":[],"title_canon_sha256":"16ebe51c44abe87be41360ba890c8ef767f3eee948c8a466e333d5f7ac7059da","abstract_canon_sha256":"00dd3caea0592647d8daf9d5d0975595f18fd81c02a9d68973a6e06caa4cebf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:16.240511Z","signature_b64":"0iXdst0DuRNn2e5J+ndzfWP5UrHDNweioXOgKcGCTiHsojPi6TyzjT97ubx+32NIEGf//vc0bF56xymq/o81BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1b8c7965f3f5d130f170ea4e1d4d57c14ee3c47593d9a33316e95e814000fc6","last_reissued_at":"2026-05-18T00:13:16.239872Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:16.239872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"View-volume Network for Semantic Scene Completion from a Single Depth Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xin Tong, Yu-Xiao Guo","submitted_at":"2018-06-14T04:42:05Z","abstract_excerpt":"We introduce a View-Volume convolutional neural network (VVNet) for inferring the occupancy and semantic labels of a volumetric 3D scene from a single depth image. The VVNet concatenates a 2D view CNN and a 3D volume CNN with a differentiable projection layer. Given a single RGBD image, our method extracts the detailed geometric features from the input depth image with a 2D view CNN and then projects the features into a 3D volume according to the input depth map via a projection layer. After that, we learn the 3D context information of the scene with a 3D volume CNN for computing the result vo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05361","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":""},"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":"1806.05361","created_at":"2026-05-18T00:13:16.239962+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05361v1","created_at":"2026-05-18T00:13:16.239962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05361","created_at":"2026-05-18T00:13:16.239962+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G4MPFS7H5OR","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G4MPFS7H5ORGDYX","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G4MPFS7","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22461","citing_title":"SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ","json":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ.json","graph_json":"https://pith.science/api/pith-number/4G4MPFS7H5ORGDYXB2SODVGVPQ/graph.json","events_json":"https://pith.science/api/pith-number/4G4MPFS7H5ORGDYXB2SODVGVPQ/events.json","paper":"https://pith.science/paper/4G4MPFS7"},"agent_actions":{"view_html":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ","download_json":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ.json","view_paper":"https://pith.science/paper/4G4MPFS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05361&json=true","fetch_graph":"https://pith.science/api/pith-number/4G4MPFS7H5ORGDYXB2SODVGVPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4G4MPFS7H5ORGDYXB2SODVGVPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ/action/storage_attestation","attest_author":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ/action/author_attestation","sign_citation":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ/action/citation_signature","submit_replication":"https://pith.science/pith/4G4MPFS7H5ORGDYXB2SODVGVPQ/action/replication_record"}},"created_at":"2026-05-18T00:13:16.239962+00:00","updated_at":"2026-05-18T00:13:16.239962+00:00"}