{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A6IBFJ5R4C6KH4GHYMV2WNBZHL","short_pith_number":"pith:A6IBFJ5R","schema_version":"1.0","canonical_sha256":"079012a7b1e0bca3f0c7c32bab34393ae14eeca11ade6e7e2820678e9a70cfcd","source":{"kind":"arxiv","id":"2210.04127","version":1},"attestation_state":"computed","paper":{"title":"Towards Efficient Neural Scene Graphs by Learning Consistency Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaerin Kong, Joonseok Lee, Nojun Kwak, Seoyoung Lee, Yeji Song","submitted_at":"2022-10-09T00:44:44Z","abstract_excerpt":"Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \\cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy ray marching for every image frame becomes a huge burden. In this paper, taking advantage of significant redundancy across adjacent frames in videos, we propose a feature-reusing framework. From the first try of naively reusing the NSG features, however, we learn that it is crucial to disentangle object-intrinsic properties consistent across frames from tran"},"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":"2210.04127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T00:44:44Z","cross_cats_sorted":[],"title_canon_sha256":"9c5e74f72c17b76a342a3165a0035737229560908b473433be3c1f3453ccf6c8","abstract_canon_sha256":"4bad4e2028d0564c32aa7641a9bd544833878ce8661b00e29ebe12501e7994b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:36.478075Z","signature_b64":"5549de6/PrtcAJGMaE3FMvdgS5GGpkXqLNWux2c47KqSzYs7zWIvz4KG5SnxQmRIU9P3D73Iz7CAYCqA5kGiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"079012a7b1e0bca3f0c7c32bab34393ae14eeca11ade6e7e2820678e9a70cfcd","last_reissued_at":"2026-07-05T05:04:36.477607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:36.477607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient Neural Scene Graphs by Learning Consistency Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaerin Kong, Joonseok Lee, Nojun Kwak, Seoyoung Lee, Yeji Song","submitted_at":"2022-10-09T00:44:44Z","abstract_excerpt":"Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \\cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy ray marching for every image frame becomes a huge burden. In this paper, taking advantage of significant redundancy across adjacent frames in videos, we propose a feature-reusing framework. From the first try of naively reusing the NSG features, however, we learn that it is crucial to disentangle object-intrinsic properties consistent across frames from tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04127","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/2210.04127/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":"2210.04127","created_at":"2026-07-05T05:04:36.477663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04127v1","created_at":"2026-07-05T05:04:36.477663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04127","created_at":"2026-07-05T05:04:36.477663+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6IBFJ5R4C6K","created_at":"2026-07-05T05:04:36.477663+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6IBFJ5R4C6KH4GH","created_at":"2026-07-05T05:04:36.477663+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6IBFJ5R","created_at":"2026-07-05T05:04:36.477663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20965","citing_title":"DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL","json":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL.json","graph_json":"https://pith.science/api/pith-number/A6IBFJ5R4C6KH4GHYMV2WNBZHL/graph.json","events_json":"https://pith.science/api/pith-number/A6IBFJ5R4C6KH4GHYMV2WNBZHL/events.json","paper":"https://pith.science/paper/A6IBFJ5R"},"agent_actions":{"view_html":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL","download_json":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL.json","view_paper":"https://pith.science/paper/A6IBFJ5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04127&json=true","fetch_graph":"https://pith.science/api/pith-number/A6IBFJ5R4C6KH4GHYMV2WNBZHL/graph.json","fetch_events":"https://pith.science/api/pith-number/A6IBFJ5R4C6KH4GHYMV2WNBZHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL/action/storage_attestation","attest_author":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL/action/author_attestation","sign_citation":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL/action/citation_signature","submit_replication":"https://pith.science/pith/A6IBFJ5R4C6KH4GHYMV2WNBZHL/action/replication_record"}},"created_at":"2026-07-05T05:04:36.477663+00:00","updated_at":"2026-07-05T05:04:36.477663+00:00"}