{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4UYBBM5MZVBAP4AWASIRITAGSG","short_pith_number":"pith:4UYBBM5M","schema_version":"1.0","canonical_sha256":"e53010b3accd4207f0160491144c0691b2bb6d57227b69ac7f8417da5a0c4161","source":{"kind":"arxiv","id":"2409.04482","version":1},"attestation_state":"computed","paper":{"title":"SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Junyi Wang, Wantong Duan, Yongtang Bao, Yue Qi, Yuze Wang","submitted_at":"2024-09-06T03:36:12Z","abstract_excerpt":"This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem."},"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":"2409.04482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T03:36:12Z","cross_cats_sorted":[],"title_canon_sha256":"b1b467eefb4831085a4b42de526dade0a8ff788da5503e66587c37f37b65197c","abstract_canon_sha256":"e2d64af5ff123973cfe8434659750ef90489202abc61712e721f184fae8e4345"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:12.770398Z","signature_b64":"ujx8YPHGEahGU2UFuibrmJTElsDfXATuob7npSTfnsjuQeTdbLPwDVwVdwsnAt73vIAg4hs0S2ps0lJJsXOEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e53010b3accd4207f0160491144c0691b2bb6d57227b69ac7f8417da5a0c4161","last_reissued_at":"2026-07-05T09:04:12.769907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:12.769907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Junyi Wang, Wantong Duan, Yongtang Bao, Yue Qi, Yuze Wang","submitted_at":"2024-09-06T03:36:12Z","abstract_excerpt":"This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04482","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/2409.04482/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":"2409.04482","created_at":"2026-07-05T09:04:12.769969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04482v1","created_at":"2026-07-05T09:04:12.769969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04482","created_at":"2026-07-05T09:04:12.769969+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UYBBM5MZVBA","created_at":"2026-07-05T09:04:12.769969+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UYBBM5MZVBAP4AW","created_at":"2026-07-05T09:04:12.769969+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UYBBM5M","created_at":"2026-07-05T09:04:12.769969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19903","citing_title":"Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG","json":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG.json","graph_json":"https://pith.science/api/pith-number/4UYBBM5MZVBAP4AWASIRITAGSG/graph.json","events_json":"https://pith.science/api/pith-number/4UYBBM5MZVBAP4AWASIRITAGSG/events.json","paper":"https://pith.science/paper/4UYBBM5M"},"agent_actions":{"view_html":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG","download_json":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG.json","view_paper":"https://pith.science/paper/4UYBBM5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04482&json=true","fetch_graph":"https://pith.science/api/pith-number/4UYBBM5MZVBAP4AWASIRITAGSG/graph.json","fetch_events":"https://pith.science/api/pith-number/4UYBBM5MZVBAP4AWASIRITAGSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG/action/storage_attestation","attest_author":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG/action/author_attestation","sign_citation":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG/action/citation_signature","submit_replication":"https://pith.science/pith/4UYBBM5MZVBAP4AWASIRITAGSG/action/replication_record"}},"created_at":"2026-07-05T09:04:12.769969+00:00","updated_at":"2026-07-05T09:04:12.769969+00:00"}