{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FF2EU552DW2UO5D5EAVPHFPKSZ","short_pith_number":"pith:FF2EU552","schema_version":"1.0","canonical_sha256":"29744a77ba1db547747d202af395ea964b553765ec49412794cff95bf9ecb2b0","source":{"kind":"arxiv","id":"1908.06297","version":1},"attestation_state":"computed","paper":{"title":"Rotation Invariant Convolutions for 3D Point Clouds Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binh-Son Hua, David W. Rosen, Sai-Kit Yeung, Zhiyuan Zhang","submitted_at":"2019-08-17T12:31:57Z","abstract_excerpt":"Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks being trained with data augmented with rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is "},"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":"1908.06297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-17T12:31:57Z","cross_cats_sorted":[],"title_canon_sha256":"66ed199df69b0ac277977a269acef0bfd7a1b53cbf4213b0a73a809fd32061d4","abstract_canon_sha256":"36be407329bb3123954c832859e2c8cee8d711889c57e8847be1d6ea498ac23b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:14.384811Z","signature_b64":"uZF2jzwe7ZITqPyOIz2dgshgoYnPTlI0po0Om+aC7J0577UcDX+X9uzZuaL/cOUma6cn8a5I0zuyECrC8hJwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29744a77ba1db547747d202af395ea964b553765ec49412794cff95bf9ecb2b0","last_reissued_at":"2026-07-04T23:58:14.384428Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:14.384428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rotation Invariant Convolutions for 3D Point Clouds Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binh-Son Hua, David W. Rosen, Sai-Kit Yeung, Zhiyuan Zhang","submitted_at":"2019-08-17T12:31:57Z","abstract_excerpt":"Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks being trained with data augmented with rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06297","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/1908.06297/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":"1908.06297","created_at":"2026-07-04T23:58:14.384484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06297v1","created_at":"2026-07-04T23:58:14.384484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06297","created_at":"2026-07-04T23:58:14.384484+00:00"},{"alias_kind":"pith_short_12","alias_value":"FF2EU552DW2U","created_at":"2026-07-04T23:58:14.384484+00:00"},{"alias_kind":"pith_short_16","alias_value":"FF2EU552DW2UO5D5","created_at":"2026-07-04T23:58:14.384484+00:00"},{"alias_kind":"pith_short_8","alias_value":"FF2EU552","created_at":"2026-07-04T23:58:14.384484+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/FF2EU552DW2UO5D5EAVPHFPKSZ","json":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ.json","graph_json":"https://pith.science/api/pith-number/FF2EU552DW2UO5D5EAVPHFPKSZ/graph.json","events_json":"https://pith.science/api/pith-number/FF2EU552DW2UO5D5EAVPHFPKSZ/events.json","paper":"https://pith.science/paper/FF2EU552"},"agent_actions":{"view_html":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ","download_json":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ.json","view_paper":"https://pith.science/paper/FF2EU552","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06297&json=true","fetch_graph":"https://pith.science/api/pith-number/FF2EU552DW2UO5D5EAVPHFPKSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FF2EU552DW2UO5D5EAVPHFPKSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ/action/storage_attestation","attest_author":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ/action/author_attestation","sign_citation":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ/action/citation_signature","submit_replication":"https://pith.science/pith/FF2EU552DW2UO5D5EAVPHFPKSZ/action/replication_record"}},"created_at":"2026-07-04T23:58:14.384484+00:00","updated_at":"2026-07-04T23:58:14.384484+00:00"}