Metraipolis › archive › dc_bcb1c6a3d720
GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors — arXiv:2609.02349
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02349
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:50:01.441Z
- SHA-256 of the archived text
b036f775d9e105c75835cf8f61dfc68a9e00725e46ed6f3e14f1649056512a8f- Stable URL of this page
https://metraipolis.com/documento/dc_bcb1c6a3d720
How to cite
GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors — arXiv:2609.02349 — arXiv (en), https://arxiv.org/abs/2609.02349 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcb1c6a3d720 (Metraipolis archive dc_bcb1c6a3d720, sha256 b036f775d9e105c75835cf8f61dfc68a9e00725e46ed6f3e14f1649056512a8f)
BibTeX
@misc{dcbcb1c6a3d720,
title = {GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors — arXiv:2609.02349},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02349},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcb1c6a3d720; sha256 b036f775d9e105c75835cf8f61dfc68a9e00725e46ed6f3e14f1649056512a8f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02349. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arranged text or rare characters. Existing approaches either improve native text rendering through stronger backbones and data-centric training without explicit glyph priors, or incorporate glyph priors through specialized designs that remain insufficiently accurate and robust under challenging scenarios. We introduce GlyphAnchor, a novel text-rendering enhancement method for both text-to-image and image-editing diffusion transformer models. GlyphAnchor enhances the backbone with lightweight glyph patch conditions whose positions are anchored to the target image through the model's native positional encoding. We train this capability with staged supervised finetuning and further refine it with text-aware post-training to improve robustness. We also introduce InfoTextBench, a benchmark for evaluating text-rich visual text rendering in both generation and editing settings. Experiments across multiple backbones and benchmarks, including long, complex, and densely arranged text and rare character scenarios, show that GlyphAnchor consistently improves text fidelity while preserving overall image quality. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02349 — 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 2026-10-17T05:25:58.103Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).