Metraipolis › archive › dc_4b2dd49d7293

TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering — arXiv:2610.19551

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19551
License (as archived)
CC0-1.0
Archived
2026-10-15T21:56:09.980Z
SHA-256 of the archived text
9d5b00e4b691e571aeb5db0323a5afdc6088ac2d15c272c228a725bef6d6fa3f
Stable URL of this page
https://metraipolis.com/documento/dc_4b2dd49d7293

How to cite

TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering — arXiv:2610.19551 — arXiv (en), https://arxiv.org/abs/2610.19551 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b2dd49d7293 (Metraipolis archive dc_4b2dd49d7293, sha256 9d5b00e4b691e571aeb5db0323a5afdc6088ac2d15c272c228a725bef6d6fa3f)
BibTeX
@misc{dc4b2dd49d7293,
  title = {TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering — arXiv:2610.19551},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19551},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b2dd49d7293; sha256 9d5b00e4b691e571aeb5db0323a5afdc6088ac2d15c272c228a725bef6d6fa3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19551. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-image models increasingly generate readable Chinese text that still contains local rendering defects, such as a character with an extra or missing stroke or a malformed component. Such errors are invisible to OCR and vision-language models, which are trained for recognition and are therefore invariant to the very structural deviations that define a rendering error. We formalize text rendering verification as a target-conditioned problem: given a target character and an image crop, decide whether the crop is a correct rendering of that character. Our verifier TEXTVERIFIER feeds the text tower a character's Ideographic Description Sequence (IDS) rather than a single-character symbol, and is trained on 12.7M crop-IDS pairs plus label-free "same-character, different-quality" hard pairs sampled from the training trajectory of a text-region inpainting model. To evaluate this ability we build TEXTRENDERBENCH-ZH, the first per-character benchmark for generated Chinese text, annotating position, identity, and correctness for 7,358 characters. TEXTVERIFIER reaches an F1 of 0.844, far above OCR confidence (0.526), a general VLM (0.329), and TextPecker (0.590). Used as a per-character reward for Flow-GRPO post-training, it further reduces rendering errors, showing that its score can both detect and correct errors.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.19551 — 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 2026-10-15T21:38:29.472Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).