{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X5Y6BFX4NUCFDBYCI3TKYCJHZE","short_pith_number":"pith:X5Y6BFX4","schema_version":"1.0","canonical_sha256":"bf71e096fc6d0451870246e6ac0927c90a7464668acf469228cc927a1acab33e","source":{"kind":"arxiv","id":"2301.09632","version":2},"attestation_state":"computed","paper":{"title":"HexPlane: A Fast Representation for Dynamic Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ang Cao, Justin Johnson","submitted_at":"2023-01-23T18:59:25Z","abstract_excerpt":"Modeling and re-rendering dynamic 3D scenes is a challenging task in 3D vision. Prior approaches build on NeRF and rely on implicit representations. This is slow since it requires many MLP evaluations, constraining real-world applications. We show that dynamic 3D scenes can be explicitly represented by six planes of learned features, leading to an elegant solution we call HexPlane. A HexPlane computes features for points in spacetime by fusing vectors extracted from each plane, which is highly efficient. Pairing a HexPlane with a tiny MLP to regress output colors and training via volume render"},"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":"2301.09632","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-23T18:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"a02bed54ef79c218f867a0dbd9ceedf670c3ab8ee8e984203014d6cc42d45c67","abstract_canon_sha256":"ce68f7aab54a55acfd4844dd6c8179dfca0caef9beeac21414400c9f869c7e5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:56.755509Z","signature_b64":"hEqyDAsFs/LKkqp6RBQ4ge6qVWNsniuw6sS0bi8mdtkYYlShXp6W/qyqDUwKIcpcWRoLmC+degeXq4x+Ug7+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf71e096fc6d0451870246e6ac0927c90a7464668acf469228cc927a1acab33e","last_reissued_at":"2026-07-05T05:54:56.755014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:56.755014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HexPlane: A Fast Representation for Dynamic Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ang Cao, Justin Johnson","submitted_at":"2023-01-23T18:59:25Z","abstract_excerpt":"Modeling and re-rendering dynamic 3D scenes is a challenging task in 3D vision. Prior approaches build on NeRF and rely on implicit representations. This is slow since it requires many MLP evaluations, constraining real-world applications. We show that dynamic 3D scenes can be explicitly represented by six planes of learned features, leading to an elegant solution we call HexPlane. A HexPlane computes features for points in spacetime by fusing vectors extracted from each plane, which is highly efficient. Pairing a HexPlane with a tiny MLP to regress output colors and training via volume render"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09632","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/2301.09632/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":"2301.09632","created_at":"2026-07-05T05:54:56.755072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09632v2","created_at":"2026-07-05T05:54:56.755072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09632","created_at":"2026-07-05T05:54:56.755072+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5Y6BFX4NUCF","created_at":"2026-07-05T05:54:56.755072+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5Y6BFX4NUCFDBYC","created_at":"2026-07-05T05:54:56.755072+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5Y6BFX4","created_at":"2026-07-05T05:54:56.755072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25909","citing_title":"R5DGS: Semantic-Aware 4D Gaussian Splatting with Rigid Body Constraints for Efficient Dynamic Scene Reconstruction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE","json":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE.json","graph_json":"https://pith.science/api/pith-number/X5Y6BFX4NUCFDBYCI3TKYCJHZE/graph.json","events_json":"https://pith.science/api/pith-number/X5Y6BFX4NUCFDBYCI3TKYCJHZE/events.json","paper":"https://pith.science/paper/X5Y6BFX4"},"agent_actions":{"view_html":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE","download_json":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE.json","view_paper":"https://pith.science/paper/X5Y6BFX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09632&json=true","fetch_graph":"https://pith.science/api/pith-number/X5Y6BFX4NUCFDBYCI3TKYCJHZE/graph.json","fetch_events":"https://pith.science/api/pith-number/X5Y6BFX4NUCFDBYCI3TKYCJHZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE/action/storage_attestation","attest_author":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE/action/author_attestation","sign_citation":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE/action/citation_signature","submit_replication":"https://pith.science/pith/X5Y6BFX4NUCFDBYCI3TKYCJHZE/action/replication_record"}},"created_at":"2026-07-05T05:54:56.755072+00:00","updated_at":"2026-07-05T05:54:56.755072+00:00"}