TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering

Yiyang Chen; Guo-Hua Wang; Yaoli Liu; Qing-Guo Chen; Zhao Xu; Weihua Luo; Xiujun Ma

cs.CVOct 14, 2026

TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering

Authors: Yiyang Chen, Guo-Hua Wang, Yaoli Liu, Qing-Guo Chen, Zhao Xu, Weihua Luo, Xiujun Ma

Organizations: State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China · Alibaba Group · State Key Lab of CAD&CG, Zhejiang University

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.

Figures & tables

Figure 1: Text rendering verification and its use as a reward. (A) For the character “基” in a generated image, OCR and VLM both miss the error, whereas TextVerifier correctly flags it as an error. (B) Using the per-character score as a post-training reward markedly reduces glyph errors.

Figure 2: Structure-aware dual tower and three-stage training. (a) The structure-aware CLIP-style dual encoder model architecture. (b) The three-stage training curriculum. (c) Inference procedure, and it can also serve as a reward for Flow-GRPO post-training.

Figure 3: Three-stage data construction. Left: real images pass through a data pipeline to yield stage1 data. Middle: standard glyphs are perturbed by two stroke edits into pairs. Right: early and late checkpoints of a text-region inpainting model repaint the same target character.

Figure 4: Per-character annotation examples from TextRenderBench-ZH . Images are generated by text-to-image models; each character carries a (position, identity, correctness) triple (green box: correct, red box: error), with error-versus-standard glyph pairs enlarged below.

Method	TP↑	FP↓	FN↓	TN↑	P↑	R↑	F1↑	Params	Inf.(ms)↓
PP-OCRv6 (thr $=0.90$ ) ( Zhang et al., 2026a )	223	140	419	6576	0.614	0.347	0.444	0.06B	17.2
PP-OCRv6 (best thr) ( Zhang et al., 2026a )	400	479	242	6237	0.455	0.623	0.526	0.06B	17.2
Qwen3.8-Max ( Qwen Team, 2026 )	78	66	564	6650	0.542	0.121	0.198	—	—
GPT-5.6-sol ( OpenAI, 2026b )	37	57	605	6659	0.394	0.058	0.101	—	—
Gemini 3.7 Flash ( Google DeepMind, 2026b )	347	1122	295	5594	0.236	0.540	0.329	—	—
TextPecker (Qwen3-VL-8B) ( Zhu et al., 2026 )	491	531	151	6185	0.480	0.765	0.590	8.29B	320.4

Table 1: Main results on TextRenderBench-ZH . TextVerifier ’s three-stage F1 of

0.844

is far above all baselines; the “best thr” row tunes the PP-OCRv6 confidence ( Zhang et al., 2026a ) threshold on the test set as an upper reference only. Params is the scoring-model size; Inf. is per-character median latency (ms) on the full test set.

Table 6

Figure 5: Qualitative comparison of Flow-GRPO post-training under different rewards. Given the target text, we compare Qwen-Image ( Wu et al., 2025 ) , the NED-only ablation, TextPecker ( Zhu et al., 2026 ) , and ours; Ours yields fewer glyph errors while staying aesthetically closer to Base.

Table 8

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Component	Setting
Image tower	ViT-L/16, input $128\times 128$ , patch $16$ ( $64$ patch tokens, mean-pooled); $306.4$ M params
Text tower	DeBERTa-v2 large, trained from scratch; IDS vocabulary $981$ ( $12$ operators, $965$ components, $4$ special)
Projection	per-tower MLP head to a $1024$ -d, $\ell_{2}$ -normalized shared space
Epochs	Stage 1 / 2 / 3 $=$ $2$ / $2$ / $1$
Batch per step	$96$ threshold units, $160$ replay samples, $128$ hard pairs
Loss hyperparams	$\tau{=}0.3$ ; $\theta{=}0.7$ , $m_{+}{=}0.1$ , $m_{-}{=}0.2$ , $\tau_{\theta}{=}0.05$ ; $m_{\mathrm{hp}}{=}0.05$ , $c_{\mathrm{hp}}{=}0.2$

Appendix

Table 6: Training configuration.

Figure 6: The positive and negative samples for stage‑2 synthesized using synthetic font files. The first column in each row corresponds to the positive sample, which represents the correct standard rendering of the font. The remaining columns are negative samples containing perturbations such as stroke addition and stroke removal.

Figure 7: The stage‑2 positive and negative samples synthesized using Chinese kaiti‑style vector data included in Makemeahanzi ( Kishore, 2016 ) . The first column of each row is the positive sample, representing the correct standard rendering of the font, and the rest are negative samples with perturbations such as stroke addition and stroke removal.

Figure 8: Architecture of the text-region inpainting model for Stage-3 relative pair construction. Three token groups, namely the full image, multiple target crops and character embeddings from Qwen3-0.6B ( Yang et al., 2025 ) , are concatenated along the sequence dimension. Custom attention mask and modified 3D-RoPE are adopted to enable multi‑crop training with absolute positional awareness.

Figure 9: The Stage‑3 positive and negative samples generated from different checkpoints of the inpainting model. In each pair, the first one is the positive sample produced by the later checkpoint, and the second one is the negative sample. For each paired positive‑negative sample, the positive sample exhibits better quality than its negative counterpart.

Figure 10: The IDS representation of Chinese characters. Left: basic decompositions, where components shared across characters are color-coded (日, 女, 木), so structurally related characters overlap at the symbol level. Middle: the twelve IDS structural operators. Right: IDS is recursive—a character expands into a tree of operators and components (想

=

相心

=

木目心)—and identical subtrees are reused across characters (相

=

木目 recurs in 想, 霜, 箱). Structural operators are shown only inside the figure.

Figure 11: Text-tower geometry versus symbolic structure (Stage-3 checkpoints). Left: text-embedding cosine for $26{,}136$ fixed-seed character pairs grouped by normalized IDS edit distance (blue: IDS tower; red: single-character tower; box = IQR, line = median). The IDS tower’s cosine falls monotonically as structural distance grows (medians $0.65\to 0.05$ ; Spearman $\rho=-0.70$ ), while the single-character tower is nearly flat ( $0.46\to 0.23$ ; $\rho=-0.34$ ). Right: the same pairs stratified by shared top-level IDS operator: same vs. different medians $0.25$ vs. $0.12$ (IDS) and $0.28$ vs. $0.24$ (single-character). Pairs form a distance-stratified diagnostic sample; distances are flat token edit distances on IDS prefixes.

$K$	$\delta$	P	R	F1	TP/FP/FN/TN
1	0.0408	0.775	0.804	0.789	516/150/126/6566
2	0.0346	0.803	0.799	0.801	513/126/129/6590
4	0.0284	0.836	0.815	0.825	523/103/119/6613
6	0.0253	0.813	0.827	0.820	531/122/111/6594
8	0.0231	0.827	0.847	0.837	544/114/98/6602
10	0.0214	0.830	0.858	0.844	551/113/91/6603

Appendix

Table 7:

K

sweep on the gold test set (

N{=}7{,}358

642

positives), frozen

90

th-percentile readout, Stage-3 model.

Figure 12: Additional TextRenderBench-ZH annotated examples.

Figure 13: Additional Flow-GRPO qualitative comparisons on oneID-ZH ( Chang et al., 2025 ) bench.

Explore similar work

Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering
Sep 29, 2026Yazhen Xie, Xingsong Ye, Zhineng ChenT2I Generation RL for Image Generation
Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI
TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
Feb 24, 2026Hanshen Zhu, Yuliang Liu, Xuecheng Wu +7RL for Image Generation T2I Generation Evaluation
Huazhong University of Science and Technology · ByteDance
TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
May 19, 2026Mingxuan Cui, Jingpu Yang, Fengxian Ji +7Diffusion Model Alignment Reward Modeling
Mohamed bin Zayed University of Artificial Intelligence · Chinese Academy of Sciences Institute of Automation · Northeastern University +1

Sep 29, 2026J/K move · Enter open · S save

Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering

Yazhen Xie, Xingsong Ye, Zhineng Chen

Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI

T2I Generation RL for Image Generation Optical Character Recognition T2I Diffusion Models

Open paper AskPDF arXiv

Rendering accurate Chinese text remains challenging for text-to-image models. Existing OCR-based reinforcement-learning rewards compare decoded transcripts with target strings. Such rewards overlook the compositional nature of Chinese writing: an ideograph consists of reusable components arranged through explicit spatial relations, yet OCR evaluates it as an atomic character. Consequently, visually different radical-level errors may receive equally coarse feedback, encouraging glyphs that merely resemble the target instead of faithfully reproducing its internal structure. We employ Ideographic Description Sequences (IDS), which comprise spatial operators and character components, and train an expert IDS recognizer to transcribe rendered Chinese text into this representation. Building on this recognizer, we introduce IDSpect, which deterministically decomposes the target text into IDS tokens and aligns crop-level visual IDS predictions with the target sequence. Globally unique token credit makes this comparison robust to the order of detected text regions. Combined with a whole-character semantic reward, IDSpect supplies fine-grained credit with component and spatial-relation without changing the image generator or adding inference-time cost. Experiments with GRPO post-training of Qwen-Image demonstrate that IDSpect achieves leading structural quality and semantic alignment on LongText and GenTextEval.

Abstract

Explore similar work

Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering

TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering

TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards