{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GMIYSCS5S3XLSNX72EJWRWKEG4","short_pith_number":"pith:GMIYSCS5","schema_version":"1.0","canonical_sha256":"3311890a5d96eeb936ffd11368d944373c8b48e10b73a45e68e5d52fd9932c11","source":{"kind":"arxiv","id":"2411.18667","version":1},"attestation_state":"computed","paper":{"title":"Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haihong Xiao, Hao Liu, Minglin Chen, Yanni Ma, Ying He","submitted_at":"2024-11-27T16:11:45Z","abstract_excerpt":"Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are computationally demanding and memory-intensive during pre-training due to the inherent nature of volume rendering. In this paper, we propose an efficient framework named GS$^3$ to learn point cloud representation, which seamlessly integrates fast 3D Gaussian Splatting into the rendering-based framework. The core idea behind our framework is to pre-train the point cloud "},"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":"2411.18667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:11:45Z","cross_cats_sorted":[],"title_canon_sha256":"1e44b2a543a9e9a0a65672d76b171667a5d471b0abb3297b191157c1e77c86c4","abstract_canon_sha256":"e4a9bf620b0efd793b24c8676cba49e812034ef72770e5ee053c5ab228bd1198"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:49.170286Z","signature_b64":"14q9PkpM/v2w0QojlHJucY8OtqDV3PUY8n5+tI3IN4RmhrkzKbjjamrbRvhha99XUEheNK9/KhRcWyUrQcGjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3311890a5d96eeb936ffd11368d944373c8b48e10b73a45e68e5d52fd9932c11","last_reissued_at":"2026-07-05T09:41:49.169809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:49.169809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haihong Xiao, Hao Liu, Minglin Chen, Yanni Ma, Ying He","submitted_at":"2024-11-27T16:11:45Z","abstract_excerpt":"Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are computationally demanding and memory-intensive during pre-training due to the inherent nature of volume rendering. In this paper, we propose an efficient framework named GS$^3$ to learn point cloud representation, which seamlessly integrates fast 3D Gaussian Splatting into the rendering-based framework. The core idea behind our framework is to pre-train the point cloud "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18667","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/2411.18667/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":"2411.18667","created_at":"2026-07-05T09:41:49.169866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18667v1","created_at":"2026-07-05T09:41:49.169866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18667","created_at":"2026-07-05T09:41:49.169866+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMIYSCS5S3XL","created_at":"2026-07-05T09:41:49.169866+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMIYSCS5S3XLSNX7","created_at":"2026-07-05T09:41:49.169866+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMIYSCS5","created_at":"2026-07-05T09:41:49.169866+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/GMIYSCS5S3XLSNX72EJWRWKEG4","json":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4.json","graph_json":"https://pith.science/api/pith-number/GMIYSCS5S3XLSNX72EJWRWKEG4/graph.json","events_json":"https://pith.science/api/pith-number/GMIYSCS5S3XLSNX72EJWRWKEG4/events.json","paper":"https://pith.science/paper/GMIYSCS5"},"agent_actions":{"view_html":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4","download_json":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4.json","view_paper":"https://pith.science/paper/GMIYSCS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18667&json=true","fetch_graph":"https://pith.science/api/pith-number/GMIYSCS5S3XLSNX72EJWRWKEG4/graph.json","fetch_events":"https://pith.science/api/pith-number/GMIYSCS5S3XLSNX72EJWRWKEG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4/action/storage_attestation","attest_author":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4/action/author_attestation","sign_citation":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4/action/citation_signature","submit_replication":"https://pith.science/pith/GMIYSCS5S3XLSNX72EJWRWKEG4/action/replication_record"}},"created_at":"2026-07-05T09:41:49.169866+00:00","updated_at":"2026-07-05T09:41:49.169866+00:00"}