{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XHEUH4JUJ4YP4LOSGEZYY6ORCT","short_pith_number":"pith:XHEUH4JU","schema_version":"1.0","canonical_sha256":"b9c943f1344f30fe2dd231338c79d114f9e6cc1222dbff97eae3a114874c6ac6","source":{"kind":"arxiv","id":"2306.08045","version":2},"attestation_state":"computed","paper":{"title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Damien Robert, Hugo Raguet, Loic Landrieu","submitted_at":"2023-06-13T18:03:05Z","abstract_excerpt":"We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES ("},"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":"2306.08045","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T18:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"85aa0df7f678665241f8bd90b8976d73bf18b870044941b8b482f2e67c172955","abstract_canon_sha256":"1b32a6182b7ac7342f1893fa889201c45d3e5e15e79967d5cfa62659664e2db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:34.750737Z","signature_b64":"hDyvnlycegSf7i8d0ckdtOqg5MVgFXMEg+u+G1VyeswbylD4PfZ3+6c3iHjRFZZEjO62NWfAap2fson0PwjNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c943f1344f30fe2dd231338c79d114f9e6cc1222dbff97eae3a114874c6ac6","last_reissued_at":"2026-07-05T06:40:34.750237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:34.750237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Damien Robert, Hugo Raguet, Loic Landrieu","submitted_at":"2023-06-13T18:03:05Z","abstract_excerpt":"We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08045","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.08045/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":"2306.08045","created_at":"2026-07-05T06:40:34.750294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08045v2","created_at":"2026-07-05T06:40:34.750294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08045","created_at":"2026-07-05T06:40:34.750294+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHEUH4JUJ4YP","created_at":"2026-07-05T06:40:34.750294+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHEUH4JUJ4YP4LOS","created_at":"2026-07-05T06:40:34.750294+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHEUH4JU","created_at":"2026-07-05T06:40:34.750294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08979","citing_title":"Towards Generalized Range-View LiDAR Segmentation in Adverse Weather","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT","json":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT.json","graph_json":"https://pith.science/api/pith-number/XHEUH4JUJ4YP4LOSGEZYY6ORCT/graph.json","events_json":"https://pith.science/api/pith-number/XHEUH4JUJ4YP4LOSGEZYY6ORCT/events.json","paper":"https://pith.science/paper/XHEUH4JU"},"agent_actions":{"view_html":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT","download_json":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT.json","view_paper":"https://pith.science/paper/XHEUH4JU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08045&json=true","fetch_graph":"https://pith.science/api/pith-number/XHEUH4JUJ4YP4LOSGEZYY6ORCT/graph.json","fetch_events":"https://pith.science/api/pith-number/XHEUH4JUJ4YP4LOSGEZYY6ORCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT/action/storage_attestation","attest_author":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT/action/author_attestation","sign_citation":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT/action/citation_signature","submit_replication":"https://pith.science/pith/XHEUH4JUJ4YP4LOSGEZYY6ORCT/action/replication_record"}},"created_at":"2026-07-05T06:40:34.750294+00:00","updated_at":"2026-07-05T06:40:34.750294+00:00"}