{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7353FRLU6WZOUNAD4SMQHZXK4L","short_pith_number":"pith:7353FRLU","schema_version":"1.0","canonical_sha256":"fefbb2c574f5b2ea3403e49903e6eae2d23d6b209e69970f39e06e9bdf804cb9","source":{"kind":"arxiv","id":"2211.12368","version":1},"attestation_state":"computed","paper":{"title":"Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Gang Zeng, Hang Zhou, Jiaxiang Tang, Jingdong Wang, Jingtuo Liu, Kaisiyuan Wang, Tianshu Hu, Xiaokang Chen","submitted_at":"2022-11-22T16:03:11Z","abstract_excerpt":"While dynamic Neural Radiance Fields (NeRF) have shown success in high-fidelity 3D modeling of talking portraits, the slow training and inference speed severely obstruct their potential usage. In this paper, we propose an efficient NeRF-based framework that enables real-time synthesizing of talking portraits and faster convergence by leveraging the recent success of grid-based NeRF. Our key insight is to decompose the inherently high-dimensional talking portrait representation into three low-dimensional feature grids. Specifically, a Decomposed Audio-spatial Encoding Module models the dynamic "},"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":"2211.12368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T16:03:11Z","cross_cats_sorted":[],"title_canon_sha256":"0e4e47e91cb2f6cd1fa6553d2d3cde051a691d07c945d28c83de708522b9f9d3","abstract_canon_sha256":"846373992c722f391442225bdbe3439ff0c216a6ed07d5c6c770a33790dca969"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:16.486206Z","signature_b64":"HyJiywgLzj7lrMLSZ+7w9zX4clDdeez/nM6ZXbahlbSCPo1rgjsA38mB5lli5eKMygFd061XhP4v1qJ7ftFmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fefbb2c574f5b2ea3403e49903e6eae2d23d6b209e69970f39e06e9bdf804cb9","last_reissued_at":"2026-07-05T05:18:16.485773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:16.485773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Gang Zeng, Hang Zhou, Jiaxiang Tang, Jingdong Wang, Jingtuo Liu, Kaisiyuan Wang, Tianshu Hu, Xiaokang Chen","submitted_at":"2022-11-22T16:03:11Z","abstract_excerpt":"While dynamic Neural Radiance Fields (NeRF) have shown success in high-fidelity 3D modeling of talking portraits, the slow training and inference speed severely obstruct their potential usage. In this paper, we propose an efficient NeRF-based framework that enables real-time synthesizing of talking portraits and faster convergence by leveraging the recent success of grid-based NeRF. Our key insight is to decompose the inherently high-dimensional talking portrait representation into three low-dimensional feature grids. Specifically, a Decomposed Audio-spatial Encoding Module models the dynamic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12368","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/2211.12368/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":"2211.12368","created_at":"2026-07-05T05:18:16.485829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12368v1","created_at":"2026-07-05T05:18:16.485829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12368","created_at":"2026-07-05T05:18:16.485829+00:00"},{"alias_kind":"pith_short_12","alias_value":"7353FRLU6WZO","created_at":"2026-07-05T05:18:16.485829+00:00"},{"alias_kind":"pith_short_16","alias_value":"7353FRLU6WZOUNAD","created_at":"2026-07-05T05:18:16.485829+00:00"},{"alias_kind":"pith_short_8","alias_value":"7353FRLU","created_at":"2026-07-05T05:18:16.485829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22865","citing_title":"MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L","json":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L.json","graph_json":"https://pith.science/api/pith-number/7353FRLU6WZOUNAD4SMQHZXK4L/graph.json","events_json":"https://pith.science/api/pith-number/7353FRLU6WZOUNAD4SMQHZXK4L/events.json","paper":"https://pith.science/paper/7353FRLU"},"agent_actions":{"view_html":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L","download_json":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L.json","view_paper":"https://pith.science/paper/7353FRLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12368&json=true","fetch_graph":"https://pith.science/api/pith-number/7353FRLU6WZOUNAD4SMQHZXK4L/graph.json","fetch_events":"https://pith.science/api/pith-number/7353FRLU6WZOUNAD4SMQHZXK4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L/action/storage_attestation","attest_author":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L/action/author_attestation","sign_citation":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L/action/citation_signature","submit_replication":"https://pith.science/pith/7353FRLU6WZOUNAD4SMQHZXK4L/action/replication_record"}},"created_at":"2026-07-05T05:18:16.485829+00:00","updated_at":"2026-07-05T05:18:16.485829+00:00"}