{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G2ILKQKCGS36MI2EX46GQPUV5V","short_pith_number":"pith:G2ILKQKC","schema_version":"1.0","canonical_sha256":"3690b5414234b7e62344bf3c683e95ed4bf83de142aa36da3f8e8524c9f85cc9","source":{"kind":"arxiv","id":"2604.19702","version":2},"attestation_state":"computed","paper":{"title":"Face Anything: 4D Face Reconstruction from Any Image Sequence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthias Nie{\\ss}ner, Richard Shaw, Simon Giebenhain, Umut Kocasari","submitted_at":"2026-04-21T17:22:39Z","abstract_excerpt":"Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and viewpoint variations occur simultaneously, creating significant ambiguity in geometry and correspondence estimation. We present a unified method for high-fidelity 4D facial reconstruction based on canonical facial point prediction, a representation that assigns each pixel a normalized facial coordinate in a shared canonical space. This formulation transforms dense tracking and dynamic reconstruction into a canonical reconstruction problem, enab"},"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":"2604.19702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T17:22:39Z","cross_cats_sorted":[],"title_canon_sha256":"1a0920c5b30e0bd009bdfd3a4d86b145668d6a4d3ef143dbcd94d9ac74282d99","abstract_canon_sha256":"2e2d803d8ce73bcf9281fb4804a8e6733575ce432f92b0ae4092ca6e8931dde0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:21.348797Z","signature_b64":"8i3QGxPgVX7KvpMPjwWamkMrO6JMzuBM3sdOtcF77SHenLNhov6nmvA5Z9sYXVVIY7BJmXXlWT6VC3mgxXpWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3690b5414234b7e62344bf3c683e95ed4bf83de142aa36da3f8e8524c9f85cc9","last_reissued_at":"2026-06-30T02:17:21.348221Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:21.348221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Face Anything: 4D Face Reconstruction from Any Image Sequence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthias Nie{\\ss}ner, Richard Shaw, Simon Giebenhain, Umut Kocasari","submitted_at":"2026-04-21T17:22:39Z","abstract_excerpt":"Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and viewpoint variations occur simultaneously, creating significant ambiguity in geometry and correspondence estimation. We present a unified method for high-fidelity 4D facial reconstruction based on canonical facial point prediction, a representation that assigns each pixel a normalized facial coordinate in a shared canonical space. This formulation transforms dense tracking and dynamic reconstruction into a canonical reconstruction problem, enab"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By jointly predicting depth and canonical coordinates, our method enables accurate depth estimation, temporally stable reconstruction, dense 3D geometry, and robust facial point tracking within a single architecture.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That multi-view geometry data can be reliably non-rigidly warped into a shared canonical space to train a model that then generalizes to arbitrary single-view image sequences without additional constraints or post-processing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A single transformer model jointly predicts depth and normalized canonical coordinates to deliver state-of-the-art 4D facial geometry and tracking with 3x lower correspondence error and 16% better depth accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0c973eedaf73717e87a7c0c4ec4e891fbd622e54a8db687148c229a89559509a"},"source":{"id":"2604.19702","kind":"arxiv","version":2},"verdict":{"id":"b3bba5ef-5e97-4d41-a539-ac790fad971d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T02:35:12.216586Z","strongest_claim":"By jointly predicting depth and canonical coordinates, our method enables accurate depth estimation, temporally stable reconstruction, dense 3D geometry, and robust facial point tracking within a single architecture.","one_line_summary":"A single transformer model jointly predicts depth and normalized canonical coordinates to deliver state-of-the-art 4D facial geometry and tracking with 3x lower correspondence error and 16% better depth accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That multi-view geometry data can be reliably non-rigidly warped into a shared canonical space to train a model that then generalizes to arbitrary single-view image sequences without additional constraints or post-processing.","pith_extraction_headline":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19702/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T16:33:35.140812Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T02:38:43.976560Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1ba399b336e0736b6e79eade72f0e67c10684a7e920254469fa34e01b24e72c8"},"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":"2604.19702","created_at":"2026-06-30T02:17:21.348311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.19702v2","created_at":"2026-06-30T02:17:21.348311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19702","created_at":"2026-06-30T02:17:21.348311+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2ILKQKCGS36","created_at":"2026-06-30T02:17:21.348311+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2ILKQKCGS36MI2E","created_at":"2026-06-30T02:17:21.348311+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2ILKQKC","created_at":"2026-06-30T02:17:21.348311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27659","citing_title":"GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V","json":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V.json","graph_json":"https://pith.science/api/pith-number/G2ILKQKCGS36MI2EX46GQPUV5V/graph.json","events_json":"https://pith.science/api/pith-number/G2ILKQKCGS36MI2EX46GQPUV5V/events.json","paper":"https://pith.science/paper/G2ILKQKC"},"agent_actions":{"view_html":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V","download_json":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V.json","view_paper":"https://pith.science/paper/G2ILKQKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.19702&json=true","fetch_graph":"https://pith.science/api/pith-number/G2ILKQKCGS36MI2EX46GQPUV5V/graph.json","fetch_events":"https://pith.science/api/pith-number/G2ILKQKCGS36MI2EX46GQPUV5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V/action/storage_attestation","attest_author":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V/action/author_attestation","sign_citation":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V/action/citation_signature","submit_replication":"https://pith.science/pith/G2ILKQKCGS36MI2EX46GQPUV5V/action/replication_record"}},"created_at":"2026-06-30T02:17:21.348311+00:00","updated_at":"2026-06-30T02:17:21.348311+00:00"}