跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-14AI 評分45

TextVerifier:超越識別,驗證中文文字渲染

TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering

AI 導讀

TEXTVERIFIER 將中文文字渲染驗證建模為目標條件判斷,在 TEXTRENDERBENCH-ZH 取得 0.844 F1,高於 OCR confidence(0.526)、通用 VLM(0.329)及 TextPecker(0.590)。

正文

Published on Oct 14

Authors:

,

,

,

,

,

Abstract

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.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.19551

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.19551 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.19551 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.19551 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co