{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LTP6I7TUQZ2GON3XJX3FBVW4JH","short_pith_number":"pith:LTP6I7TU","schema_version":"1.0","canonical_sha256":"5cdfe47e7486746737774df650d6dc49fe401b356d9859b9f03b06cd6956dd22","source":{"kind":"arxiv","id":"2401.03764","version":1},"attestation_state":"computed","paper":{"title":"3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Peng Zheng, Rui Ma, Ruiqi Liu, Ye Wang","submitted_at":"2024-01-08T09:41:07Z","abstract_excerpt":"Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. However, most of them cannot support the fine-grained part-level control over synthesized images. Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities. To address these issues, we propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis. First, a simple yet effective depth-guided 2D-to-3D lifting modu"},"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":"2401.03764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-08T09:41:07Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"65bd562d5d2b3e8f675c823d3b07614e0fd6207adf6154669b5d83751d8952d6","abstract_canon_sha256":"a3fe6668a323f943ef26609979da86df99f2396b2bfc21931464c65904935530"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:13.504926Z","signature_b64":"IqY571ku5Fy22xVfPLNiJBs5+zW0j4Bhc81kBome/MFqdAffN4su8q0LV7IB76RbKtHMm/CLpj5/hgNj9IB6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cdfe47e7486746737774df650d6dc49fe401b356d9859b9f03b06cd6956dd22","last_reissued_at":"2026-07-05T07:31:13.504590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:13.504590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Peng Zheng, Rui Ma, Ruiqi Liu, Ye Wang","submitted_at":"2024-01-08T09:41:07Z","abstract_excerpt":"Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. However, most of them cannot support the fine-grained part-level control over synthesized images. Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities. To address these issues, we propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis. First, a simple yet effective depth-guided 2D-to-3D lifting modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03764","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/2401.03764/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":"2401.03764","created_at":"2026-07-05T07:31:13.504648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03764v1","created_at":"2026-07-05T07:31:13.504648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03764","created_at":"2026-07-05T07:31:13.504648+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTP6I7TUQZ2G","created_at":"2026-07-05T07:31:13.504648+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTP6I7TUQZ2GON3X","created_at":"2026-07-05T07:31:13.504648+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTP6I7TU","created_at":"2026-07-05T07:31:13.504648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06770","citing_title":"SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH","json":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH.json","graph_json":"https://pith.science/api/pith-number/LTP6I7TUQZ2GON3XJX3FBVW4JH/graph.json","events_json":"https://pith.science/api/pith-number/LTP6I7TUQZ2GON3XJX3FBVW4JH/events.json","paper":"https://pith.science/paper/LTP6I7TU"},"agent_actions":{"view_html":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH","download_json":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH.json","view_paper":"https://pith.science/paper/LTP6I7TU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03764&json=true","fetch_graph":"https://pith.science/api/pith-number/LTP6I7TUQZ2GON3XJX3FBVW4JH/graph.json","fetch_events":"https://pith.science/api/pith-number/LTP6I7TUQZ2GON3XJX3FBVW4JH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH/action/storage_attestation","attest_author":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH/action/author_attestation","sign_citation":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH/action/citation_signature","submit_replication":"https://pith.science/pith/LTP6I7TUQZ2GON3XJX3FBVW4JH/action/replication_record"}},"created_at":"2026-07-05T07:31:13.504648+00:00","updated_at":"2026-07-05T07:31:13.504648+00:00"}