Metraipolis › archive › dc_677adfffb05f
TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters — arXiv:2608.19637
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19637
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:04:34.251Z
- SHA-256 of the archived text
d75bcf61e5f688c068e8143535d8ca52355ddb8362776a080d8cf6d7f91b8200- Stable URL of this page
https://metraipolis.com/documento/dc_677adfffb05f
How to cite
TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters — arXiv:2608.19637 — arXiv (en), https://arxiv.org/abs/2608.19637 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_677adfffb05f (Metraipolis archive dc_677adfffb05f, sha256 d75bcf61e5f688c068e8143535d8ca52355ddb8362776a080d8cf6d7f91b8200)
BibTeX
@misc{dc677adfffb05f,
title = {TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters — arXiv:2608.19637},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19637},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_677adfffb05f; sha256 d75bcf61e5f688c068e8143535d8ca52355ddb8362776a080d8cf6d7f91b8200},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19637. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition. Despite recent progress in instruction-based image editing, general-purpose models remain unreliable in this setting: they often omit or incorrectly render the target text, place it over salient products or pre-existing content, and produce structurally distorted or visually inconsistent glyphs. We introduce \textbf{TextRefine}, a task-aligned post-training framework that combines supervised fine-tuning with operation-specific reward optimization to address these complementary failure modes. For text insertion, our text-span-level reward jointly assesses semantic fidelity and target-span coverage, penalizes spatial conflicts with products and existing text, and employs a gated structural constraint to preserve non-text regions. For text replacement, our glyph-level reward leverages the connectionist temporal classification (CTC) posterior of the target character to provide graded supervision for fine-grained defects, including missing strokes, structural deformations, and confusion among visually similar characters. We further introduce \textbf{OpenTextEdit}, a dataset comprising 100K images for text editing in product posters, with multi-text layouts, detailed text attributes, product masks, and challenging low-frequency characters. Extensive experiments on both insertion and replacement demonstrate that TextRefine consistently outperforms the evaluated image editing baselines in textual fidelity, placement reliability, and glyph quality while better preserving source-image content.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.19637 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T12:01:57.701Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).