{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RR3ZSWMNVGJV7OVOF2IVWCQW6W","short_pith_number":"pith:RR3ZSWMN","schema_version":"1.0","canonical_sha256":"8c7799598da9935fbaae2e915b0a16f5b69c4db01a7e62730fa0a1254451882e","source":{"kind":"arxiv","id":"2411.04724","version":1},"attestation_state":"computed","paper":{"title":"Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benito Buchheim, J\\\"urgen D\\\"ollner, Max Reimann","submitted_at":"2024-11-07T14:02:41Z","abstract_excerpt":"We present a methodology for conditional control of human shape and pose in pretrained text-to-image diffusion models using a 3D human parametric model (SMPL). Fine-tuning these diffusion models to adhere to new conditions requires large datasets and high-quality annotations, which can be more cost-effectively acquired through synthetic data generation rather than real-world data. However, the domain gap and low scene diversity of synthetic data can compromise the pretrained model's visual fidelity. We propose a domain-adaptation technique that maintains image quality by isolating syntheticall"},"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":"2411.04724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T14:02:41Z","cross_cats_sorted":[],"title_canon_sha256":"06997a5d5959177bc4865e8a7508f62a44980b2f712b0f55792c87637e7ddb93","abstract_canon_sha256":"d442733d59787afb622d4cd48359fd369e2fb0e45bb879c1e501db16396eb579"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:24.441117Z","signature_b64":"di+ay0ELIWcBzyA0ShUI33T7jUBXT1Apfyf9jFWaEwCDnTn+NToQexhvhPKTEFBL3WgJsduAiltHHgp3now2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c7799598da9935fbaae2e915b0a16f5b69c4db01a7e62730fa0a1254451882e","last_reissued_at":"2026-07-05T09:32:24.440621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:24.440621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benito Buchheim, J\\\"urgen D\\\"ollner, Max Reimann","submitted_at":"2024-11-07T14:02:41Z","abstract_excerpt":"We present a methodology for conditional control of human shape and pose in pretrained text-to-image diffusion models using a 3D human parametric model (SMPL). Fine-tuning these diffusion models to adhere to new conditions requires large datasets and high-quality annotations, which can be more cost-effectively acquired through synthetic data generation rather than real-world data. However, the domain gap and low scene diversity of synthetic data can compromise the pretrained model's visual fidelity. We propose a domain-adaptation technique that maintains image quality by isolating syntheticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04724","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/2411.04724/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":"2411.04724","created_at":"2026-07-05T09:32:24.440682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04724v1","created_at":"2026-07-05T09:32:24.440682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04724","created_at":"2026-07-05T09:32:24.440682+00:00"},{"alias_kind":"pith_short_12","alias_value":"RR3ZSWMNVGJV","created_at":"2026-07-05T09:32:24.440682+00:00"},{"alias_kind":"pith_short_16","alias_value":"RR3ZSWMNVGJV7OVO","created_at":"2026-07-05T09:32:24.440682+00:00"},{"alias_kind":"pith_short_8","alias_value":"RR3ZSWMN","created_at":"2026-07-05T09:32:24.440682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18068","citing_title":"PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W","json":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W.json","graph_json":"https://pith.science/api/pith-number/RR3ZSWMNVGJV7OVOF2IVWCQW6W/graph.json","events_json":"https://pith.science/api/pith-number/RR3ZSWMNVGJV7OVOF2IVWCQW6W/events.json","paper":"https://pith.science/paper/RR3ZSWMN"},"agent_actions":{"view_html":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W","download_json":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W.json","view_paper":"https://pith.science/paper/RR3ZSWMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04724&json=true","fetch_graph":"https://pith.science/api/pith-number/RR3ZSWMNVGJV7OVOF2IVWCQW6W/graph.json","fetch_events":"https://pith.science/api/pith-number/RR3ZSWMNVGJV7OVOF2IVWCQW6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W/action/storage_attestation","attest_author":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W/action/author_attestation","sign_citation":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W/action/citation_signature","submit_replication":"https://pith.science/pith/RR3ZSWMNVGJV7OVOF2IVWCQW6W/action/replication_record"}},"created_at":"2026-07-05T09:32:24.440682+00:00","updated_at":"2026-07-05T09:32:24.440682+00:00"}