{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7X6FATX3IEFH6DV5EW7OMEJVKO","short_pith_number":"pith:7X6FATX3","schema_version":"1.0","canonical_sha256":"fdfc504efb410a7f0ebd25bee6113553ae044151740e665beef3e7a432d798d0","source":{"kind":"arxiv","id":"1905.06817","version":1},"attestation_state":"computed","paper":{"title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Feng, Michael J. Black, Soubhik Sanyal, Timo Bolkart","submitted_at":"2019-05-16T14:57:45Z","abstract_excerpt":"The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack ground truth 3D shape. To train a network without any 2D-to-3D supervision, we present RingNet, which learns to compute 3D face shape from a single image. Our key observation is that an individual's face shape is constant across images, regardless of expression, pose, lighting, etc. RingNet leverages multiple images of a person and automatically detect"},"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":"1905.06817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-16T14:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"dbe3515ff7d013fe89dbb6a00ebdd717d9d3d77f37db53262f32fbc1cd2d611b","abstract_canon_sha256":"623f30a145fb644cef827136d14e8064cd38aad5d9918d879cc4e7463e587e4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:00.945803Z","signature_b64":"ESgyBzjCm3CTrnF1VFCpD73Uze1PDi/VofINhh7ckODIDewMV2v2K2pam30GBCDl9iGWGPfxrxztf7zNBmjFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdfc504efb410a7f0ebd25bee6113553ae044151740e665beef3e7a432d798d0","last_reissued_at":"2026-05-17T23:46:00.943661Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:00.943661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Feng, Michael J. Black, Soubhik Sanyal, Timo Bolkart","submitted_at":"2019-05-16T14:57:45Z","abstract_excerpt":"The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack ground truth 3D shape. To train a network without any 2D-to-3D supervision, we present RingNet, which learns to compute 3D face shape from a single image. Our key observation is that an individual's face shape is constant across images, regardless of expression, pose, lighting, etc. RingNet leverages multiple images of a person and automatically detect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06817","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":""},"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":"1905.06817","created_at":"2026-05-17T23:46:00.943784+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06817v1","created_at":"2026-05-17T23:46:00.943784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06817","created_at":"2026-05-17T23:46:00.943784+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X6FATX3IEFH","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X6FATX3IEFH6DV5","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X6FATX3","created_at":"2026-05-18T12:33:12.712433+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/7X6FATX3IEFH6DV5EW7OMEJVKO","json":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO.json","graph_json":"https://pith.science/api/pith-number/7X6FATX3IEFH6DV5EW7OMEJVKO/graph.json","events_json":"https://pith.science/api/pith-number/7X6FATX3IEFH6DV5EW7OMEJVKO/events.json","paper":"https://pith.science/paper/7X6FATX3"},"agent_actions":{"view_html":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO","download_json":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO.json","view_paper":"https://pith.science/paper/7X6FATX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06817&json=true","fetch_graph":"https://pith.science/api/pith-number/7X6FATX3IEFH6DV5EW7OMEJVKO/graph.json","fetch_events":"https://pith.science/api/pith-number/7X6FATX3IEFH6DV5EW7OMEJVKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO/action/storage_attestation","attest_author":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO/action/author_attestation","sign_citation":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO/action/citation_signature","submit_replication":"https://pith.science/pith/7X6FATX3IEFH6DV5EW7OMEJVKO/action/replication_record"}},"created_at":"2026-05-17T23:46:00.943784+00:00","updated_at":"2026-05-17T23:46:00.943784+00:00"}