{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QXABGNC5DLNENL6SRVTZOY6R24","short_pith_number":"pith:QXABGNC5","schema_version":"1.0","canonical_sha256":"85c013345d1ada46afd28d679763d1d72fd52df313a0f6d2c785ae57bc09e194","source":{"kind":"arxiv","id":"2203.07881","version":1},"attestation_state":"computed","paper":{"title":"LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akin Caliskan, Alexander Richard, Emre Aksan, Jason Saragih, Otmar Hilliges, Shih-En Wei, Shugao Ma, Stanislav Pidhorskyi","submitted_at":"2022-03-15T13:22:57Z","abstract_excerpt":"Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by headset-mounted cameras or a front-facing camera, and sparse facial landmarks. To mitigate this asymmetry, we introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. Our proposed model, LiP-Flow, consists of two encoders that learn representations from the rich trainin"},"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":"2203.07881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-15T13:22:57Z","cross_cats_sorted":[],"title_canon_sha256":"8a59c3462fecd7b68db5eb894b91eacd158525bee7cd53e798e1ade4c02a6592","abstract_canon_sha256":"e33b46a944ba7ffbc9231d072b7f7709db373cf4214451277757684392cc01cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:23.779795Z","signature_b64":"gQRvBZ4KoRc/fg/K4qHS9LIfNEW3do+H7QEEikk5MxHgUKqyL4V4+7iaR4e7Gi+PqKZtIzc/tpivY3FWFCh/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85c013345d1ada46afd28d679763d1d72fd52df313a0f6d2c785ae57bc09e194","last_reissued_at":"2026-07-05T04:05:23.779459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:23.779459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akin Caliskan, Alexander Richard, Emre Aksan, Jason Saragih, Otmar Hilliges, Shih-En Wei, Shugao Ma, Stanislav Pidhorskyi","submitted_at":"2022-03-15T13:22:57Z","abstract_excerpt":"Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by headset-mounted cameras or a front-facing camera, and sparse facial landmarks. To mitigate this asymmetry, we introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. Our proposed model, LiP-Flow, consists of two encoders that learn representations from the rich trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07881","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/2203.07881/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":"2203.07881","created_at":"2026-07-05T04:05:23.779513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07881v1","created_at":"2026-07-05T04:05:23.779513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07881","created_at":"2026-07-05T04:05:23.779513+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXABGNC5DLNE","created_at":"2026-07-05T04:05:23.779513+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXABGNC5DLNENL6S","created_at":"2026-07-05T04:05:23.779513+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXABGNC5","created_at":"2026-07-05T04:05:23.779513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24","json":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24.json","graph_json":"https://pith.science/api/pith-number/QXABGNC5DLNENL6SRVTZOY6R24/graph.json","events_json":"https://pith.science/api/pith-number/QXABGNC5DLNENL6SRVTZOY6R24/events.json","paper":"https://pith.science/paper/QXABGNC5"},"agent_actions":{"view_html":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24","download_json":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24.json","view_paper":"https://pith.science/paper/QXABGNC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07881&json=true","fetch_graph":"https://pith.science/api/pith-number/QXABGNC5DLNENL6SRVTZOY6R24/graph.json","fetch_events":"https://pith.science/api/pith-number/QXABGNC5DLNENL6SRVTZOY6R24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24/action/storage_attestation","attest_author":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24/action/author_attestation","sign_citation":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24/action/citation_signature","submit_replication":"https://pith.science/pith/QXABGNC5DLNENL6SRVTZOY6R24/action/replication_record"}},"created_at":"2026-07-05T04:05:23.779513+00:00","updated_at":"2026-07-05T04:05:23.779513+00:00"}