{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PADQJG66RQ73J2J5GHB5OIIE7W","short_pith_number":"pith:PADQJG66","schema_version":"1.0","canonical_sha256":"7807049bde8c3fb4e93d31c3d72104fdbb4253a1b27fec316ee732cc27f285e8","source":{"kind":"arxiv","id":"2605.14708","version":1},"attestation_state":"computed","paper":{"title":"StyleTextGen: Style-Conditioned Multilingual Scene Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"StyleTextGen generates scene text that matches reference visual styles across languages using a dedicated dual-branch encoder.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangmin Zhao, Liu Yu, Yan Shu, Yichao Liu, Yu Zhou, Zeyu Chen","submitted_at":"2026-05-14T11:24:44Z","abstract_excerpt":"Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose StyleTextGen, a novel framework that learns to perceive and replicate visual text styles across different languages and writing systems. Our approach features three key contributions: First, we introduce a dual-branch style encoder dedicated to style modeling, yielding robust multilingual text style representations in complex real-world scenes. Second, we desig"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T11:24:44Z","cross_cats_sorted":[],"title_canon_sha256":"7e9d295f264f56563720097f63d96edad649716d38bfc6814486f3553f853f77","abstract_canon_sha256":"0667db19a66b31850f0dd9d8cdeb6d60eb029b8f0216dd0ab767a44e95764e7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:59.246572Z","signature_b64":"CrR8tTvH+Gxo6q2hESQprJzXNDlMgMx5UvmKPJ4BeRiEjhbJfIgEZPQfZ4ERwYr0V+l+48hQBc3Vl+FeBg1ADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7807049bde8c3fb4e93d31c3d72104fdbb4253a1b27fec316ee732cc27f285e8","last_reissued_at":"2026-05-17T23:38:59.246059Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:59.246059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyleTextGen: Style-Conditioned Multilingual Scene Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"StyleTextGen generates scene text that matches reference visual styles across languages using a dedicated dual-branch encoder.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangmin Zhao, Liu Yu, Yan Shu, Yichao Liu, Yu Zhou, Zeyu Chen","submitted_at":"2026-05-14T11:24:44Z","abstract_excerpt":"Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose StyleTextGen, a novel framework that learns to perceive and replicate visual text styles across different languages and writing systems. Our approach features three key contributions: First, we introduce a dual-branch style encoder dedicated to style modeling, yielding robust multilingual text style representations in complex real-world scenes. Second, we desig"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"StyleTextGen significantly outperforms existing methods in style consistency and cross-lingual generalization, establishing new state-of-the-art performance in multilingual style-conditioned text generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The dual-branch style encoder and consistency loss successfully extract and maintain precise, fine-grained text styles from complex real-world backgrounds across languages without post-hoc tuning or dataset-specific adjustments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"StyleTextGen generates scene text that matches reference visual styles across languages using a dedicated dual-branch encoder.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a4a58b41c0177bef8849557391938fcef7650b084975e924aead69aeac53d800"},"source":{"id":"2605.14708","kind":"arxiv","version":1},"verdict":{"id":"86bc7873-b64a-4568-9f04-356d2988cb97","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T04:52:00.033596Z","strongest_claim":"StyleTextGen significantly outperforms existing methods in style consistency and cross-lingual generalization, establishing new state-of-the-art performance in multilingual style-conditioned text generation.","one_line_summary":"StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The dual-branch style encoder and consistency loss successfully extract and maintain precise, fine-grained text styles from complex real-world backgrounds across languages without post-hoc tuning or dataset-specific adjustments.","pith_extraction_headline":"StyleTextGen generates scene text that matches reference visual styles across languages using a dedicated dual-branch encoder."},"references":{"count":61,"sample":[{"doi":"","year":2023,"title":"In- structpix2pix: Learning to follow image editing instructions","work_id":"273977e6-dd4b-4c1d-9f32-f13a08c04d96","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"The devil is in fine-tuning and long-tailed prob- lems: a new benchmark for scene text detection.arXiv preprint arXiv:2505.15649, 2025","work_id":"f77ba1f6-e8b7-4bf2-b13d-82139f5b7dbc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Posta: A go-to framework for customized artistic poster gen- eration","work_id":"8bdfaaf7-a8a9-4f09-b68a-bebb86151d83","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Textdiffuser-2: Unleashing the power of language models for text rendering.arXiv preprint arXiv:2311.16465, 2023","work_id":"8cc07be4-b59c-466e-b152-0a92bc8ca0d6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2305.10855 (2023) 7","work_id":"f43372f1-5688-4262-a5f2-2e8f7da8d54c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":61,"snapshot_sha256":"8cafd2d22f8cc8ad8e011b1972cac2d363c628095747ff05e4025ce4f2f76597","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"189af8e91dcf8cfd3df5ab944e9692e818db19b4ba5f23ace4f8e6964d00ed14"},"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":"2605.14708","created_at":"2026-05-17T23:38:59.246144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14708v1","created_at":"2026-05-17T23:38:59.246144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14708","created_at":"2026-05-17T23:38:59.246144+00:00"},{"alias_kind":"pith_short_12","alias_value":"PADQJG66RQ73","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"PADQJG66RQ73J2J5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"PADQJG66","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W","json":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W.json","graph_json":"https://pith.science/api/pith-number/PADQJG66RQ73J2J5GHB5OIIE7W/graph.json","events_json":"https://pith.science/api/pith-number/PADQJG66RQ73J2J5GHB5OIIE7W/events.json","paper":"https://pith.science/paper/PADQJG66"},"agent_actions":{"view_html":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W","download_json":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W.json","view_paper":"https://pith.science/paper/PADQJG66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14708&json=true","fetch_graph":"https://pith.science/api/pith-number/PADQJG66RQ73J2J5GHB5OIIE7W/graph.json","fetch_events":"https://pith.science/api/pith-number/PADQJG66RQ73J2J5GHB5OIIE7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W/action/storage_attestation","attest_author":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W/action/author_attestation","sign_citation":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W/action/citation_signature","submit_replication":"https://pith.science/pith/PADQJG66RQ73J2J5GHB5OIIE7W/action/replication_record"}},"created_at":"2026-05-17T23:38:59.246144+00:00","updated_at":"2026-05-17T23:38:59.246144+00:00"}