{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BJWDIC6MFMZSG6X7S35Z2I26WG","short_pith_number":"pith:BJWDIC6M","schema_version":"1.0","canonical_sha256":"0a6c340bcc2b33237aff96fb9d235eb1a0602a8422df3d236dbc6cfcc7c9526a","source":{"kind":"arxiv","id":"2204.11402","version":2},"attestation_state":"computed","paper":{"title":"PointInst3D: Segmenting 3D Instances by Points","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chunhua Shen, Tong He, Wei Yin","submitted_at":"2022-04-25T02:41:46Z","abstract_excerpt":"The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion. In doing so it avoids the challenges that clustering-based methods face: introducing dependencies among different tasks of the model. We find the key to its success is assigning a suitable target to each sampled point. Instead of the commonly"},"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":"2204.11402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T02:41:46Z","cross_cats_sorted":[],"title_canon_sha256":"07b3d54f1e8fb24a56a9dedae7f4e4f4169d3c92ffb079d820c450d0b8bea902","abstract_canon_sha256":"546274416789c907920c62fa3d0539eb0c01a69e42fde7a3ce549f55c7c1fc4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:49.943165Z","signature_b64":"XiP9vlUZqFOol3afetFBqr9fO+C1gSnxiCGMaVnSedjg8dO3LZe5mx0O3y8EUFo5HIBvvPU23+FiIAPBoCcoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6c340bcc2b33237aff96fb9d235eb1a0602a8422df3d236dbc6cfcc7c9526a","last_reissued_at":"2026-07-05T04:39:49.942769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:49.942769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointInst3D: Segmenting 3D Instances by Points","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chunhua Shen, Tong He, Wei Yin","submitted_at":"2022-04-25T02:41:46Z","abstract_excerpt":"The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion. In doing so it avoids the challenges that clustering-based methods face: introducing dependencies among different tasks of the model. We find the key to its success is assigning a suitable target to each sampled point. Instead of the commonly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11402","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/2204.11402/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":"2204.11402","created_at":"2026-07-05T04:39:49.942823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11402v2","created_at":"2026-07-05T04:39:49.942823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11402","created_at":"2026-07-05T04:39:49.942823+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJWDIC6MFMZS","created_at":"2026-07-05T04:39:49.942823+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJWDIC6MFMZSG6X7","created_at":"2026-07-05T04:39:49.942823+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJWDIC6M","created_at":"2026-07-05T04:39:49.942823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG","json":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG.json","graph_json":"https://pith.science/api/pith-number/BJWDIC6MFMZSG6X7S35Z2I26WG/graph.json","events_json":"https://pith.science/api/pith-number/BJWDIC6MFMZSG6X7S35Z2I26WG/events.json","paper":"https://pith.science/paper/BJWDIC6M"},"agent_actions":{"view_html":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG","download_json":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG.json","view_paper":"https://pith.science/paper/BJWDIC6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11402&json=true","fetch_graph":"https://pith.science/api/pith-number/BJWDIC6MFMZSG6X7S35Z2I26WG/graph.json","fetch_events":"https://pith.science/api/pith-number/BJWDIC6MFMZSG6X7S35Z2I26WG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG/action/storage_attestation","attest_author":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG/action/author_attestation","sign_citation":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG/action/citation_signature","submit_replication":"https://pith.science/pith/BJWDIC6MFMZSG6X7S35Z2I26WG/action/replication_record"}},"created_at":"2026-07-05T04:39:49.942823+00:00","updated_at":"2026-07-05T04:39:49.942823+00:00"}