- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In the field of text rendering, most prior methods have focused only on improving OCR scores through GRPO with appropriately designed reward functions, while overlooking localized glyph errors. However, simple OCR detectors are insensitive to error glyphs, which makes it meaningful to develop a reward model capable of detecting localized glyph defects. To this end, the paper proposes TextDART, which can estimate defect-aware text regions. Building on this, the proposed SCANNER extends the advantage computation of vanilla GRPO to the token level, allowing correct and incorrect text regions within the same generated sample to be optimized differently. Evaluations on Chinese and English text-rendering benchmarks show that, when applied to base models such as Qwen-Image and FLUX, SCANNER outperforms other methods across multiple evaluation dimensions.
Critical strengths
-
The paper proposes TextDART, which extends the previous TextPecker method to the region level, enabling the model to output defect-aware text regions in a single pass.
-
The proposed SCANNER extends GRPO advantage computation to the token level, allowing different regions to be optimized differently according to their accuracy. In addition, according to the reported experimental results, it outperforms vanilla GRPO on both Chinese and English evaluation sets.
Critical weaknesses
- Limited Novelty. Although the paper introduces several techniques to construct a region- and glyph-sensitive GRPO-style algorithm, its overall novelty remains limited.
- First, an algorithm targeting region-level glyph errors was previously introduced in GlyphPrinter (CVPR 2026) [2]. However, I do not see this work cited or included in the comparisons. To the best of my knowledge, GlyphPrinter proposes a region-level DPO algorithm and achieves strong performance on multilingual text-rendering benchmarks. In my opinion, SCANNER appears to adopt a similar idea and implement it within a GRPO framework.
- Second, the idea of region-level GRPO used in SCANNER has also been explored in prior work, SpatialFlow-GRPO[1]. Concepts such as target-level policy ratios and region-level GRPO training objectives have already been implemented in a similar form in SpatialFlow-GRPO. The only apparent distinction between SCANNER and SpatialFlow-GRPO is that SCANNER introduces a global text score during the early timesteps. However, this simple modification does not establish sufficient originality. Moreover, the reward function in Eq. (5) appears similar to one previously introduced in TextPecker[4].
- In addition, TextDART seems to be primarily a simple region-level extension of TextPecker. For example, combining a lightweight OCR detector (such as PPOCR) with TextPecker might achieve similar effectiveness and comparable inference speed.
- Insufficient Experiments and Coverage of Related Works.
- The paper focuses exclusively on text-rendering models that accept text embeddings, while overlooking models conditioned on glyph images, such as EasyText[3] and GlyphPrinter[2]. Consequently, the experimental comparisons are not sufficiently comprehensive. In particular, GlyphPrinter, which is the method most closely aligned with the motivation of this paper, is not included in the comparisons. There is therefore insufficient evidence that the proposed SCANNER offers meaningful advantages over these advanced methods.
- Furthermore, most of the qualitative cases presented in the paper focus on multi-region OCR metrics, while only a small number specifically examine glyph errors, even though glyph accuracy is the central problem the paper claims to address. I believe the model should be evaluated on more challenging benchmarks, including complex Chinese characters such as Traditional Chinese characters. To the best of my knowledge, advanced models such as Qwen-Image already achieve very high OCR and glyph accuracy in most simple scenarios. Therefore, merely outperforming other methods on relatively simple Chinese and English benchmarks is insufficient to demonstrate the practical value of the proposed SCANNER.
-
Lack of Multilingual Text-Rendering Capabilities. The paper optimizes only for Chinese and English text rendering, without considering other languages, which limits its practical applicability. By contrast, glyph-image-conditioned methods only need to learn the mapping from text rendered in a default font to text in realistic scenes, which may allow them to generalize more effectively to other settings. According to the experiments reported in GlyphPrinter, the model is post-trained only on Chinese and English DPO datasets yet generalizes well to other languages. I therefore believe that the authors should provide additional experiments and analyses to demonstrate the main advantages of their algorithm over glyph-image-conditioned methods in improving individual glyph accuracy.
-
Insufficient Theoretical Derivation. Intuitively, region-level GRPO should increase the generation probability of preferred regions while decreasing the probability of defective regions. However, the optimization objective corresponding to the GRPO formulation in Eq. (11) is not clear yet. The vanilla GRPO can be interpreted as optimizing the reward of the entire image. However, the authors do not derive the underlying optimization objective of their region-level GRPO formulation. As a result, its theoretical or physical interpretation remains unclear.
[1] Yang, Yankai, et al. “SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing.”
[2] Shuai, Xincheng, et al. "GlyphPrinter: region-grouped direct preference optimization for glyph-accurate visual text rendering."
[3] Lu, Runnan, et al. "Easytext: Controllable diffusion transformer for multilingual text rendering."
[4] Zhu, Hanshen, et al. "Textpecker: Rewarding structural anomaly quantification for enhancing visual text rendering."
Questions for authors
-
Comparison with glyph-image-conditioned models. How does SCANNER perform compared with models that take glyph images as input? Furthermore, could the authors quantify the performance gains achieved by SCANNER over competing baselines when rendering more complex glyphs, such as Traditional Chinese characters? I encourage the authors to extend the experimental evaluation to include such challenging settings. Besides, a detailed analysis of the factors underlying the improvements would further strengthen the paper.
-
Novelty relative to prior work. Apart from several minor modifications, such as the Noise-aware Schedule, what are the key differences between the motivation and region-level GRPO algorithm proposed in this paper and those of prior works such as GlyphPrinter[2] and SpatialFlow-GRPO[1]? The answer will substantially influence my assessment of the paper’s originality and novelty. Please also cite these papers appropriately in the revised version and explicitly explain how SCANNER differs from them.
-
Theoretical interpretation of Eq. (11). Similar to the analysis provided in GlyphPrinter, can the authors derive the underlying optimization objective corresponding to the GRPO algorithm in Eq. (11)? GlyphPrinter shows that its region-level DPO formulation essentially optimizes a region-level reward function together with a KL-divergence term. Can the authors derive an analogous result for SCANNER? I would like to better understand the theoretical or physical interpretation of Eq. (11).
-
Role of the Noise-aware Schedule. I am curious about the practical role of the Noise-aware Schedule. Most prior works suggest that early denoising steps largely determine the overall layout and semantic content. Therefore, the rationale for assigning a larger global mixing weight during early timesteps is unclear. Even if the image content is ambiguous under extremely high noise levels, why would increasing global feedback be more beneficial than applying region-level rewards? I therefore encourage the authors to provide a more rigorous analysis of the mechanisms through which the global reward contributes to the observed performance improvements. In addition, when computing the global reward, how do the authors ensure that the concatenation order of the detected text is consistent with that of the ground-truth text?
[1] Yang, Yankai, et al. “SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing.”
[2] Shuai, Xincheng, et al. "GlyphPrinter: region-grouped direct preference optimization for glyph-accurate visual text rendering."
9 comments
Response 2/5 — Controlled Comparisons and TextDART versus TextPecker (W1, Q2)
W1 & Q2: Novelty Relative to GlyphPrinter, SpatialFlow-GRPO, and TextPecker (Part 2)
Controlled Comparison of SCANNER and SpatialFlow-GRPO. With FLUX.1-dev and TextDART fixed, SCANNER achieves stronger overall performance (Tab. R1). The results support the benefit of SCANNER's target-level credit-assignment design beyond the reward model alone.
| RL algorithm | LongText-Bench / TextScore ↑ | OneIG-Bench / TextScore ↑ | OneIG-Bench / ED ↓ | OneIG-Bench / CR ↑ | OneIG-Bench / WAC ↑ | CVTG-2k / WordAcc ↑ | CVTG-2k / NED ↑ | GenTextEval-Bench / Qua ↑ | GenTextEval-Bench / Sem ↑ | PolyText-Bench / CS ↑ | PolyText-Bench / CG ↑ | PolyText-Bench / OG ↑ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SpatialFlow-GRPO-style | 0.822 | 0.840 | 54.08 | 0.279 | 0.589 | 0.809 | 0.900 | 0.839 | 0.612 | 0.865 | 0.883 | 0.529 |
| SCANNER | 0.827 | 0.858 | 51.06 | 0.309 | 0.598 | 0.834 | 0.914 | 0.839 | 0.613 | 0.882 | 0.905 | 0.653 |
Table R1. Controlled comparison of SpatialFlow-GRPO-style and SCANNER. SCANNER goes beyond applying existing region-level GRPO to text: its text-target credit assignment delivers stronger performance than SpatialFlow-GRPO-style training with the same backbone and reward model.
(3) TextDART vs. TextPecker(W1 & Q2)
Eq. (5) is motivated by TextPecker (as acknowledged in Section 4.1). TextPecker aggregates uniformly counted anomalies into an image-level reward. TextDART produces target-specific rewards from severity-weighted character-, word-, and block-level defects (Appendix A.8), with many-to-many matching, cross-rollout merging, and explicit missing/extra-text rewards (Appendix A.1.1).
Why OCR + TextPecker is not equivalent to TextDART. TextPecker supports box-conditioned evaluation, but each call accepts only one externally supplied box. This design depends on OCR localization and requires region-by-region evaluation, leading to three main limitations:
- OCR-first evaluation propagates false boxes and confidence-filtered omissions.
- OCR's line-oriented boxes need not match the semantic text blocks used by SCANNER.
- N boxes require N calls, making evaluation cost scale linearly with the number of regions.
TextDART jointly localizes semantic blocks and recognizes defects in one pass, mitigating these error-propagation, granularity, and efficiency bottlenecks.
We evaluate OCRv5+TextPecker alternatives, which yield weaker overall generation quality than TextDART+SCANNER (Tab. 1). Training-side measurements (Tab. R2) show that TextDART reduces per-step time by 11.6% and GPU-hours to match the baseline's final OCR score by 41.1%.
| Efficiency metric | OCR+TextPecker | TextDART |
|---|---|---|
| Time per optimizer step (s) ↓ | 366.84 | 324.24 |
| Training GPU-hours, fixed 360 steps ↓ | 1173.89 | 1037.58 |
| GPU-hours to match baseline's final OCR score ↓ | 1173.89 | 691.83 |
Table R2. Training-side efficiency on 32 H20 GPUs; the final row compares costs at the same OCR quality. OCR+TextPecker is not equivalent to TextDART in training efficiency: it requires substantially more GPU-hours to reach the same OCR quality and incurs higher per-step training cost.
The revised manuscript cites GlyphPrinter, clarifies distinctions in Appendix A.1.5, and adds the efficiency comparison in Appendix A.3.5, with the new content highlighted in blue.
Response 3/5 — Glyph-Conditioned Comparisons and Complex Traditional Chinese (W2, Q1)
W2 & Q1: Glyph-Conditioned Comparisons and Complex Glyphs
We clarify SCANNER's conditioning-agnostic scope and provide additional experiments on glyph-image-conditioned models and complex Traditional Chinese glyphs.
1. Conditioning-Agnostic Scope and Evaluation Design
- SCANNER operates during RL post-training and does not restrict the conditioning form of the base model. It can therefore optimize both prompt-conditioned and glyph-image-conditioned generators.
- Direct cross-condition comparisons measure complete system performance, while same-backbone comparisons isolate the contribution of the RL algorithm. We report both below.
Section 5.3already compares RL algorithms on FLUX and Qwen-Image. The new experiments extend this evaluation to EasyText and GlyphPrinter.- We use the official LingT2I text-rendering split [1], containing 3,000 examples across 10 languages, with paired text, scene descriptions, and glyph conditions. Gemini-4-Argon is used uniformly for text extraction and malformation evaluation.
2. Comparison with EasyText and GlyphPrinter
We evaluate the official EasyText and GlyphPrinter checkpoints and apply SCANNER to EasyText and GlyphPrinter Stage 1. In Tab. R3, SCANNER improves all six metrics on each backbone and outperforms R-GDPO on GlyphPrinter Stage 1, demonstrating benefits across both conditioning types and gains over the closest region-level preference baseline.
| Base model | Condition | Reward | RL algorithm | En NED ↑ | En Accu ↑ | En Mal. ↓ | Zh NED ↑ | Zh Accu ↑ | Zh Mal. ↓ |
|---|---|---|---|---|---|---|---|---|---|
| Qwen-Image-2512 | Prompt | — | — | 0.559 | 0.327 | 0.125 | 0.474 | 0.343 | 0.150 |
| EasyText final | Glyph | — | — | 0.948 | 0.800 | 0.068 | 0.794 | 0.627 | 0.313 |
| GlyphPrinter Stage 1 | Glyph | — | — | 0.942 | 0.827 | 0.084 | 0.909 | 0.793 | 0.152 |
| GlyphPrinter final | Glyph | — | R-GDPO | 0.944 | 0.820 | 0.140 | 0.917 | 0.773 | 0.222 |
| Qwen-Image-2512 | Prompt | TextDART | SCANNER | 0.589 | 0.350 | 0.062 | 0.481 | 0.360 | 0.083 |
| EasyText final | Glyph | TextDART | SCANNER | 0.979 | 0.917 | 0.017 | 0.893 | 0.817 | 0.091 |
| GlyphPrinter Stage 1 | Glyph | TextDART | SCANNER | 0.970 | 0.890 | 0.046 | 0.941 | 0.863 | 0.092 |
Table R3. English and Chinese results on LingT2I. Mal. denotes malformation rate. SCANNER offers meaningful advantages on glyph-image-conditioned models, improving EasyText and outperforming R-GDPO.
3. Evaluation on Complex Traditional Chinese Glyphs
We construct a 300-example generation benchmark from the public Traditional Chinese OCR test data [2]. It covers high-stroke, rare, long-text, multi-region, rotated, and vertical text, with 50 paired examples per category. Text, scenes, and layouts are matched across conditioning forms. We will release the benchmark upon acceptance.
As shown in Tab. R4, SCANNER improves both metrics in all six categories for all three backbones, directly quantifying its gains on complex glyphs.
| Method | Condition | High-stroke | Rare | Long text | Multi-region | Rotated | Vertical |
|---|---|---|---|---|---|---|---|
| Qwen-Image-2512 | Prompt | 0.283/0.071 | 0.253/0.099 | 0.935/0.029 | 0.741/0.076 | 0.288/0.054 | 0.947/0.272 |
| EasyText | Glyph | 0.342/0.356 | 0.475/0.238 | 0.560/0.609 | 0.836/0.051 | 0.252/0.601 | 0.879/0.203 |
| GlyphPrinter Stage 1 | Glyph | 0.075/0.210 | 0.240/0.117 | 0.157/0.172 | 0.757/0.016 | 0.130/0.229 | 0.824/0.508 |
| GlyphPrinter final | Glyph | 0.255/0.083 | 0.438/0.072 | 0.287/0.261 | 0.643/0.004 | 0.259/0.122 | 0.949/0.463 |
| Qwen-Image-2512 + SCANNER | Prompt | 0.286/0.031 | 0.270/0.049 | 0.963/0.004 | 0.857/0.005 | 0.298/0.037 | 0.953/0.018 |
| EasyText + SCANNER | Glyph | 0.350/0.138 | 0.478/0.217 | 0.720/0.469 | 0.882/0.000 | 0.350/0.364 | 0.900/0.137 |
| GlyphPrinter Stage 1 + SCANNER | Glyph | 0.286/0.045 | 0.498/0.062 | 0.377/0.139 | 0.938/0.003 | 0.295/0.092 | 0.951/0.046 |
Table R4. Complex Traditional Chinese evaluation. Each cell reports Character NED ↑ / malformation rate ↓. SCANNER’s benefits extend to complex Traditional Chinese glyphs, improving character accuracy and reducing glyph malformations across high-stroke, rare-character, and challenging layout settings.
4. Glyph-Specific Evidence and Factors Underlying Improvements
- Qualitative cases and glyph metrics: Figures 4, 10, 15, and 16 in the original manuscript contain 17 cases with highlighted glyph errors, where SCANNER renders the corresponding text correctly. GenTextEval-Bench and PolyText-Bench also provide glyph-related quantitative metrics.
- Target-consistent credit: The substantial long-text and multi-region gains are consistent with cross-rollout target alignment and explicit modeling of missing and extra text.
- Glyph-sensitive evaluation: High-stroke and rare-character improvements, particularly the reduced malformation rates, are consistent with severity-weighted target rewards and localized credit assignment.
We have included these additional experimental results in Appendix A.3.11 and A.3.12 of the revised manuscript, with the new content highlighted in blue.
Response 1/5 — Novelty Relative to GlyphPrinter and SpatialFlow-GRPO (W1, Q2)
Thanks for your detailed and technically insightful feedback. We appreciate the recognition of TextDART's single-pass region-level defect perception and SCANNER's effectiveness on both Chinese and English generation. Below, we provide a point-by-point response to your concerns and questions.
W1 & Q2: Novelty Relative to GlyphPrinter, SpatialFlow-GRPO, and TextPecker (Part 1 of 2)
Our contribution is reliable text-target credit assignment under freely generated layouts. In prompt-only generation, requested text has a known identity but no predefined spatial support: its location and detection granularity vary across rollouts, and it may be split, merged, or omitted. Reliable optimization therefore requires establishing which regions represent the same target, how their defects should be evaluated, and when their spatial support should guide denoising updates. TextDART and SCANNER jointly address these challenges through defect-aware localization, cross-rollout target construction, and noise-dependent credit assignment.
(1) SCANNER vs. R-GDPO:
GlyphPrinter's R-GDPO learns from offline annotated regional preferences, which specify the regions to favor or suppress. However, in prompt-only online generation, establishing reliable regional supervision is itself a central challenge: text locations and detection granularity vary across rollouts, while requested content may be split, merged, or omitted. Consequently, detected regions do not automatically provide consistent units for reward comparison and credit assignment.
SCANNER addresses this challenge by constructing content-consistent, defect-aware target supervision online:
The resulting contribution is an online mechanism for establishing what to compare and where to assign credit when neither text regions nor their cross-sample correspondence are given in advance.
(2) SCANNER vs. SpatialFlow-GRPO
SpatialFlow-GRPO provides semantic-region feedback for image editing and normalizes regional rewards within instruction–label groups. For freely generated text, the critical challenge is making the comparison units consistent when detection boundaries and target coverage change across rollouts. Furthermore, spatial support inferred from the final image may not be equally suitable for assigning credit at every denoising step. SCANNER addresses these issues through four connected designs:
Appendix A.1.1).Appendix A.1.2).Appendix A.1.3).Appendix A.1.4).