{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6D5KPWZ37USWGD2KEVXTRFOGHJ","short_pith_number":"pith:6D5KPWZ3","schema_version":"1.0","canonical_sha256":"f0faa7db3bfd25630f4a256f3895c63a727a77d607f74199a2258196e2ad1f6f","source":{"kind":"arxiv","id":"2303.14243","version":1},"attestation_state":"computed","paper":{"title":"DyLiN: Making Light Field Networks Dynamic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Yu, Joel Julin, Koichiro Niinuma, Laszlo A. Jeni, Zoltan A. Milacski","submitted_at":"2023-03-24T19:05:48Z","abstract_excerpt":"Light Field Networks, the re-formulations of radiance fields to oriented rays, are magnitudes faster than their coordinate network counterparts, and provide higher fidelity with respect to representing 3D structures from 2D observations. They would be well suited for generic scene representation and manipulation, but suffer from one problem: they are limited to holistic and static scenes. In this paper, we propose the Dynamic Light Field Network (DyLiN) method that can handle non-rigid deformations, including topological changes. We learn a deformation field from input rays to canonical rays, "},"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":"2303.14243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T19:05:48Z","cross_cats_sorted":[],"title_canon_sha256":"5f92db2e47d6eef0b751d0e669c8edc0b8920bc622dd7096e02210297cf0d182","abstract_canon_sha256":"f59e40a63c638b12ea314a434ec6c74b9e541f8b2f58a25153449b9782d5288b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:38.584585Z","signature_b64":"IxqNltjb9dvFq0+PHUOFVXvTu5KYL85DlAwSLjJmKfeeYiJh9aRWhpnxOCRRZsAZeI7jwaCuB7vdaiANzd2UBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0faa7db3bfd25630f4a256f3895c63a727a77d607f74199a2258196e2ad1f6f","last_reissued_at":"2026-07-05T05:54:38.584191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:38.584191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyLiN: Making Light Field Networks Dynamic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Yu, Joel Julin, Koichiro Niinuma, Laszlo A. Jeni, Zoltan A. Milacski","submitted_at":"2023-03-24T19:05:48Z","abstract_excerpt":"Light Field Networks, the re-formulations of radiance fields to oriented rays, are magnitudes faster than their coordinate network counterparts, and provide higher fidelity with respect to representing 3D structures from 2D observations. They would be well suited for generic scene representation and manipulation, but suffer from one problem: they are limited to holistic and static scenes. In this paper, we propose the Dynamic Light Field Network (DyLiN) method that can handle non-rigid deformations, including topological changes. We learn a deformation field from input rays to canonical rays, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14243","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/2303.14243/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":"2303.14243","created_at":"2026-07-05T05:54:38.584247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14243v1","created_at":"2026-07-05T05:54:38.584247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14243","created_at":"2026-07-05T05:54:38.584247+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D5KPWZ37USW","created_at":"2026-07-05T05:54:38.584247+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D5KPWZ37USWGD2K","created_at":"2026-07-05T05:54:38.584247+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D5KPWZ3","created_at":"2026-07-05T05:54:38.584247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15732","citing_title":"DynamicAvatars: Accurate Dynamic Facial Avatars Reconstruction and Precise Editing with Diffusion Models","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ","json":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ.json","graph_json":"https://pith.science/api/pith-number/6D5KPWZ37USWGD2KEVXTRFOGHJ/graph.json","events_json":"https://pith.science/api/pith-number/6D5KPWZ37USWGD2KEVXTRFOGHJ/events.json","paper":"https://pith.science/paper/6D5KPWZ3"},"agent_actions":{"view_html":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ","download_json":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ.json","view_paper":"https://pith.science/paper/6D5KPWZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14243&json=true","fetch_graph":"https://pith.science/api/pith-number/6D5KPWZ37USWGD2KEVXTRFOGHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6D5KPWZ37USWGD2KEVXTRFOGHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ/action/storage_attestation","attest_author":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ/action/author_attestation","sign_citation":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ/action/citation_signature","submit_replication":"https://pith.science/pith/6D5KPWZ37USWGD2KEVXTRFOGHJ/action/replication_record"}},"created_at":"2026-07-05T05:54:38.584247+00:00","updated_at":"2026-07-05T05:54:38.584247+00:00"}