{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A26YFLGDL3STBJSGAFQE3DH5HG","short_pith_number":"pith:A26YFLGD","schema_version":"1.0","canonical_sha256":"06bd82acc35ee530a64601604d8cfd39a42b5794fc4f713e7027dd406c84f9e5","source":{"kind":"arxiv","id":"2310.08579","version":2},"attestation_state":"computed","paper":{"title":"HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Dahua Lin, Ivan Skorokhodov, Jian Ren, Sergey Tulyakov, Xian Liu, Xihui Liu, Yanyu Li, Ziwei Liu","submitted_at":"2023-10-12T17:59:34Z","abstract_excerpt":"Despite significant advances in large-scale text-to-image models, achieving hyper-realistic human image generation remains a desirable yet unsolved task. Existing models like Stable Diffusion and DALL-E 2 tend to generate human images with incoherent parts or unnatural poses. To tackle these challenges, our key insight is that human image is inherently structural over multiple granularities, from the coarse-level body skeleton to fine-grained spatial geometry. Therefore, capturing such correlations between the explicit appearance and latent structure in one model is essential to generate coher"},"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":"2310.08579","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"6f5b4ffa3a227edc5c57e5e57b3e89087e8774764b37e112ab63b22bbc711d59","abstract_canon_sha256":"cbb8984ba19022c4f4127eb0db36c24779e88ebbbfe0f052046a3c64640d7fa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:17.760681Z","signature_b64":"JeBTgrXStVe+1huP3d7jG0km2u7BqUZAAlCeOGUUIJ4p+J00oWDtsPOHJxRiCX4xtmVt5HG5TfwlF7NZlx0EAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06bd82acc35ee530a64601604d8cfd39a42b5794fc4f713e7027dd406c84f9e5","last_reissued_at":"2026-07-05T07:56:17.760107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:17.760107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Dahua Lin, Ivan Skorokhodov, Jian Ren, Sergey Tulyakov, Xian Liu, Xihui Liu, Yanyu Li, Ziwei Liu","submitted_at":"2023-10-12T17:59:34Z","abstract_excerpt":"Despite significant advances in large-scale text-to-image models, achieving hyper-realistic human image generation remains a desirable yet unsolved task. Existing models like Stable Diffusion and DALL-E 2 tend to generate human images with incoherent parts or unnatural poses. To tackle these challenges, our key insight is that human image is inherently structural over multiple granularities, from the coarse-level body skeleton to fine-grained spatial geometry. Therefore, capturing such correlations between the explicit appearance and latent structure in one model is essential to generate coher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08579","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/2310.08579/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":"2310.08579","created_at":"2026-07-05T07:56:17.760187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08579v2","created_at":"2026-07-05T07:56:17.760187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08579","created_at":"2026-07-05T07:56:17.760187+00:00"},{"alias_kind":"pith_short_12","alias_value":"A26YFLGDL3ST","created_at":"2026-07-05T07:56:17.760187+00:00"},{"alias_kind":"pith_short_16","alias_value":"A26YFLGDL3STBJSG","created_at":"2026-07-05T07:56:17.760187+00:00"},{"alias_kind":"pith_short_8","alias_value":"A26YFLGD","created_at":"2026-07-05T07:56:17.760187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25759","citing_title":"Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19720","citing_title":"ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG","json":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG.json","graph_json":"https://pith.science/api/pith-number/A26YFLGDL3STBJSGAFQE3DH5HG/graph.json","events_json":"https://pith.science/api/pith-number/A26YFLGDL3STBJSGAFQE3DH5HG/events.json","paper":"https://pith.science/paper/A26YFLGD"},"agent_actions":{"view_html":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG","download_json":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG.json","view_paper":"https://pith.science/paper/A26YFLGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08579&json=true","fetch_graph":"https://pith.science/api/pith-number/A26YFLGDL3STBJSGAFQE3DH5HG/graph.json","fetch_events":"https://pith.science/api/pith-number/A26YFLGDL3STBJSGAFQE3DH5HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG/action/storage_attestation","attest_author":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG/action/author_attestation","sign_citation":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG/action/citation_signature","submit_replication":"https://pith.science/pith/A26YFLGDL3STBJSGAFQE3DH5HG/action/replication_record"}},"created_at":"2026-07-05T07:56:17.760187+00:00","updated_at":"2026-07-05T07:56:17.760187+00:00"}