{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NI2DXHXWY2KRII6AWWQGTQSH7Z","short_pith_number":"pith:NI2DXHXW","schema_version":"1.0","canonical_sha256":"6a343b9ef6c6951423c0b5a069c247fe5db91b10c5f7664d4efc846bb807356c","source":{"kind":"arxiv","id":"2004.02122","version":1},"attestation_state":"computed","paper":{"title":"Anisotropic Convolutional Networks for 3D Semantic Scene Completion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Li, Kai Han, Peng Wang, Xia Yuan, Yu Liu","submitted_at":"2020-04-05T07:57:02Z","abstract_excerpt":"As a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the stan"},"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":"2004.02122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-05T07:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"e1a6992c697e0977a9842ae6c9f11cac3766bfb8702abc0edc83d0584b92a787","abstract_canon_sha256":"fbc609f3904f0c3f5fc881f3b9e4d0e4c75c2f21ef0a09b5c044dd85eb3ff021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:56.150593Z","signature_b64":"krqKjO4kQa3EcfEgAcda2tSl0TvdP3kwiVtN0lXP7HDpS9miRZxriN7J6RbncuK/2Cdxh8KcnWYCSH/ElwF6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a343b9ef6c6951423c0b5a069c247fe5db91b10c5f7664d4efc846bb807356c","last_reissued_at":"2026-07-05T00:52:56.150238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:56.150238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anisotropic Convolutional Networks for 3D Semantic Scene Completion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Li, Kai Han, Peng Wang, Xia Yuan, Yu Liu","submitted_at":"2020-04-05T07:57:02Z","abstract_excerpt":"As a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the stan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02122","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/2004.02122/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":"2004.02122","created_at":"2026-07-05T00:52:56.150295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02122v1","created_at":"2026-07-05T00:52:56.150295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02122","created_at":"2026-07-05T00:52:56.150295+00:00"},{"alias_kind":"pith_short_12","alias_value":"NI2DXHXWY2KR","created_at":"2026-07-05T00:52:56.150295+00:00"},{"alias_kind":"pith_short_16","alias_value":"NI2DXHXWY2KRII6A","created_at":"2026-07-05T00:52:56.150295+00:00"},{"alias_kind":"pith_short_8","alias_value":"NI2DXHXW","created_at":"2026-07-05T00:52:56.150295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12218","citing_title":"Physics-Informed Linear Model (PILM): Analytical Representations and Application to Crustal Strain Rate Estimation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z","json":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z.json","graph_json":"https://pith.science/api/pith-number/NI2DXHXWY2KRII6AWWQGTQSH7Z/graph.json","events_json":"https://pith.science/api/pith-number/NI2DXHXWY2KRII6AWWQGTQSH7Z/events.json","paper":"https://pith.science/paper/NI2DXHXW"},"agent_actions":{"view_html":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z","download_json":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z.json","view_paper":"https://pith.science/paper/NI2DXHXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02122&json=true","fetch_graph":"https://pith.science/api/pith-number/NI2DXHXWY2KRII6AWWQGTQSH7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/NI2DXHXWY2KRII6AWWQGTQSH7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z/action/storage_attestation","attest_author":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z/action/author_attestation","sign_citation":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z/action/citation_signature","submit_replication":"https://pith.science/pith/NI2DXHXWY2KRII6AWWQGTQSH7Z/action/replication_record"}},"created_at":"2026-07-05T00:52:56.150295+00:00","updated_at":"2026-07-05T00:52:56.150295+00:00"}