{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:W7DIUZXMDGYVTDLOKMTUASSF7S","short_pith_number":"pith:W7DIUZXM","schema_version":"1.0","canonical_sha256":"b7c68a66ec19b1598d6e5327404a45fca0ddb92e6376d013bd2a6ffa13324210","source":{"kind":"arxiv","id":"1903.08527","version":2},"attestation_state":"computed","paper":{"title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Chen, Jiaolong Yang, Sicheng Xu, Xin Tong, Yu Deng, Yunde Jia","submitted_at":"2019-03-20T14:44:45Z","abstract_excerpt":"Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce. In this paper, we propose a novel deep 3D face reconstruction approach that 1) leverages a robust, hybrid loss function for weakly-supervised learning which takes into account both low-level and perception-level information for supervision, and 2) performs multi-image face reconstruction by exploiting complementary information fro"},"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":"1903.08527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-20T14:44:45Z","cross_cats_sorted":[],"title_canon_sha256":"be6f071c9338d7316516d0dffaa5f5381c4123e81ac1942756784603937c11c5","abstract_canon_sha256":"756c72a370a0bcb2c53c118d75930f15574fd1349892c5782d7cd1e54cf068dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:01.129471Z","signature_b64":"WaSzd5bgCLCvyCrUXnC1DJo5RSeqTym8lw/T1CMW0+B2J6iOFk63P0KDsMsazboiRyEQpHxQb5T3XnVLSwkjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7c68a66ec19b1598d6e5327404a45fca0ddb92e6376d013bd2a6ffa13324210","last_reissued_at":"2026-07-05T00:54:01.128980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:01.128980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Chen, Jiaolong Yang, Sicheng Xu, Xin Tong, Yu Deng, Yunde Jia","submitted_at":"2019-03-20T14:44:45Z","abstract_excerpt":"Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce. In this paper, we propose a novel deep 3D face reconstruction approach that 1) leverages a robust, hybrid loss function for weakly-supervised learning which takes into account both low-level and perception-level information for supervision, and 2) performs multi-image face reconstruction by exploiting complementary information fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08527","kind":"arxiv","version":2},"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/1903.08527/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":"1903.08527","created_at":"2026-07-05T00:54:01.129037+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08527v2","created_at":"2026-07-05T00:54:01.129037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08527","created_at":"2026-07-05T00:54:01.129037+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7DIUZXMDGYV","created_at":"2026-07-05T00:54:01.129037+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7DIUZXMDGYVTDLO","created_at":"2026-07-05T00:54:01.129037+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7DIUZXM","created_at":"2026-07-05T00:54:01.129037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03996","citing_title":"3D Human Face Reconstruction with 3DMM face model from RGB image","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S","json":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S.json","graph_json":"https://pith.science/api/pith-number/W7DIUZXMDGYVTDLOKMTUASSF7S/graph.json","events_json":"https://pith.science/api/pith-number/W7DIUZXMDGYVTDLOKMTUASSF7S/events.json","paper":"https://pith.science/paper/W7DIUZXM"},"agent_actions":{"view_html":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S","download_json":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S.json","view_paper":"https://pith.science/paper/W7DIUZXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08527&json=true","fetch_graph":"https://pith.science/api/pith-number/W7DIUZXMDGYVTDLOKMTUASSF7S/graph.json","fetch_events":"https://pith.science/api/pith-number/W7DIUZXMDGYVTDLOKMTUASSF7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S/action/storage_attestation","attest_author":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S/action/author_attestation","sign_citation":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S/action/citation_signature","submit_replication":"https://pith.science/pith/W7DIUZXMDGYVTDLOKMTUASSF7S/action/replication_record"}},"created_at":"2026-07-05T00:54:01.129037+00:00","updated_at":"2026-07-05T00:54:01.129037+00:00"}