{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCE7GTQ3QM3VJD5DJ3VSA5QE4R","short_pith_number":"pith:MCE7GTQ3","schema_version":"1.0","canonical_sha256":"6089f34e1b8337548fa34eeb207604e44fcfcd265ff900659fab6c62369e4cc1","source":{"kind":"arxiv","id":"2403.10783","version":1},"attestation_state":"computed","paper":{"title":"StableGarment: Garment-Centric Generation via Stable Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibo Zhao, Hailong Guo, Hao Tang, Huaxia Li, Jiaming Liu, Peipei Li, Rui Wang, Xu Tang, Yao Hu","submitted_at":"2024-03-16T03:05:07Z","abstract_excerpt":"In this paper, we introduce StableGarment, a unified framework to tackle garment-centric(GC) generation tasks, including GC text-to-image, controllable GC text-to-image, stylized GC text-to-image, and robust virtual try-on. The main challenge lies in retaining the intricate textures of the garment while maintaining the flexibility of pre-trained Stable Diffusion. Our solution involves the development of a garment encoder, a trainable copy of the denoising UNet equipped with additive self-attention (ASA) layers. These ASA layers are specifically devised to transfer detailed garment textures, al"},"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":"2403.10783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T03:05:07Z","cross_cats_sorted":[],"title_canon_sha256":"d97b3f752621f7d3760037d12a2951b693a11a15b0d2059dcdc08c0660d898e4","abstract_canon_sha256":"cb10cc4f10710daa41b048c179fbeae36c7ee9ed484eb3a10b072692572ef437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:06.874654Z","signature_b64":"io9WYyB+W0zUaFrS8NdxPWB7MvVKSwmd/Hb4V5Za4sdU2ltiR92Q76wtMqDHDb7Z37j1Wyd13BLG/7/bJfrtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6089f34e1b8337548fa34eeb207604e44fcfcd265ff900659fab6c62369e4cc1","last_reissued_at":"2026-07-05T07:57:06.874192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:06.874192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StableGarment: Garment-Centric Generation via Stable Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibo Zhao, Hailong Guo, Hao Tang, Huaxia Li, Jiaming Liu, Peipei Li, Rui Wang, Xu Tang, Yao Hu","submitted_at":"2024-03-16T03:05:07Z","abstract_excerpt":"In this paper, we introduce StableGarment, a unified framework to tackle garment-centric(GC) generation tasks, including GC text-to-image, controllable GC text-to-image, stylized GC text-to-image, and robust virtual try-on. The main challenge lies in retaining the intricate textures of the garment while maintaining the flexibility of pre-trained Stable Diffusion. Our solution involves the development of a garment encoder, a trainable copy of the denoising UNet equipped with additive self-attention (ASA) layers. These ASA layers are specifically devised to transfer detailed garment textures, al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10783","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/2403.10783/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":"2403.10783","created_at":"2026-07-05T07:57:06.874244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10783v1","created_at":"2026-07-05T07:57:06.874244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10783","created_at":"2026-07-05T07:57:06.874244+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCE7GTQ3QM3V","created_at":"2026-07-05T07:57:06.874244+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCE7GTQ3QM3VJD5D","created_at":"2026-07-05T07:57:06.874244+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCE7GTQ3","created_at":"2026-07-05T07:57:06.874244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04881","citing_title":"DiverAge: Reliable Pluralistic Face Aging with Cross-Age Identity Relation Guidance","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23178","citing_title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07210","citing_title":"VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R","json":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R.json","graph_json":"https://pith.science/api/pith-number/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/graph.json","events_json":"https://pith.science/api/pith-number/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/events.json","paper":"https://pith.science/paper/MCE7GTQ3"},"agent_actions":{"view_html":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R","download_json":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R.json","view_paper":"https://pith.science/paper/MCE7GTQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10783&json=true","fetch_graph":"https://pith.science/api/pith-number/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/graph.json","fetch_events":"https://pith.science/api/pith-number/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/action/storage_attestation","attest_author":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/action/author_attestation","sign_citation":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/action/citation_signature","submit_replication":"https://pith.science/pith/MCE7GTQ3QM3VJD5DJ3VSA5QE4R/action/replication_record"}},"created_at":"2026-07-05T07:57:06.874244+00:00","updated_at":"2026-07-05T07:57:06.874244+00:00"}