Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies

Carlos Garrido-Munoz; Aniello Panariello; Silvia Cascianelli; Angelo Porrello; Simone Calderara; Jorge Calvo-Zaragoza; Rita Cucchiara

cs.CVApr 8, 2026

Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies

Authors: Carlos Garrido-Munoz, Aniello Panariello, Silvia Cascianelli, Angelo Porrello, Simone Calderara, Jorge Calvo-Zaragoza, Rita Cucchiara

Organizations: University of Alicante, Spain · University of Modena and Reggio Emilia, Italy

Abstract

Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully zero-shot synthetic-to-real generalization setting, where no real data from the target language is available. Our approach learns how model parameters change when moving from synthetic to real handwriting in one or more source languages and transfers this learned correction to new target languages. When using multiple sources, we rely on linguistic similarity to weigh their contrubition when combining them. Experiments across five languages and six architectures show consistent improvements over synthetic-only baselines and reveal that the transferred corrections benefit even languages unrelated to the sources.

Figures & tables

Figure 1: Example of Single Analogy Merging: Estimating the Spanish real-domain model ( $\theta_{\text{es}}^{\text{real}}$ ) by transferring the synthetic-to-real displacement vector ( $\Delta_{\text{it}}^{\text{s2r}}$ ) learned from the Italian domain.

Figure 2: Multilingual analogy merging framework for Zero-Shot Synthetic-to-Real HTR. We estimate the target real model $\theta_{T}^{\text{real}}$ by combining synthetic-to-real displacement vectors $\Delta_{S}^{\text{s2r}}$ from multiple sources $\mathcal{S}$ . These vectors are weighted by linguistically informed coefficients $\beta_{s}$ derived from source language $S$ and synthetic target $T$ similarity, achieving zero-shot adaptation ( Eq. 6 ).

TrOCR (S) [ 32 ]

TrOCR (B) [ 32 ]

TrOCR (L) [ 32 ]

CRNN [ 50 ]

VAN [ 13 ]

HTR-VT [ 33 ]

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

In-domain

5.0

16.7

4.4

14.8

4.3

14.1

4.2

16.0

5.4

21.8

5.3

21.8

Baseline

\theta_{T}^{syn}

39.7 (+0.0)

72.4 (+0.0)

37.7 (+0.0)

69.1 (+0.0)

36.2 (+0.0)

67.8 (+0.0)

38.8 (+0.0)

75.6 (+0.0)

35.2 (+0.0)

76.3 (+0.0)

41.7 (+0.0)

81.8 (+0.0)

Single analogy

\beta=1

37.9\text{{\color[rgb]{0,0.6,0}\scriptsize(-1.8)}}

72.8\text{{\color[rgb]{1,0,0}\scriptsize(+0.4)}}

36.9\text{{\color[rgb]{0,0.6,0}\scriptsize(-0.8)}}

70.9\text{{\color[rgb]{1,0,0}\scriptsize(+1.8)}}

35.3\text{{\color[rgb]{0,0.6,0}\scriptsize(-0.9)}}

73.1\text{{\color[rgb]{1,0,0}\scriptsize(+5.3)}}

35.9\text{{\color[rgb]{0,0.6,0}\scriptsize(-2.9)}}

73.3\text{{\color[rgb]{0,0.6,0}\scriptsize(-2.2)}}

34.5\text{{\color[rgb]{0,0.6,0}\scriptsize(-0.7)}}

78.0\text{{\color[rgb]{1,0,0}\scriptsize(+1.7)}}

40.6\text{{\color[rgb]{0,0.6,0}\scriptsize(-1.1)}}

83.7\text{{\color[rgb]{1,0,0}\scriptsize(+1.9)}}

\beta=\beta_{\text{KL}}

35.0\text{{\color[rgb]{0,0.6,0}\scriptsize(-4.7)}}

68.2\text{{\color[rgb]{0,0.6,0}\scriptsize(-4.2)}}

32.9\text{{\color[rgb]{0,0.6,0}\scriptsize(-4.8)}}

64.6\text{{\color[rgb]{0,0.6,0}\scriptsize(-4.5)}}

32.4\text{{\color[rgb]{0,0.6,0}\scriptsize(-3.8)}}

64.5\text{{\color[rgb]{0,0.6,0}\scriptsize(-3.3)}}

35.4\text{{\color[rgb]{0,0.6,0}\scriptsize(-3.4)}}

70.0\text{{\color[rgb]{0,0.6,0}\scriptsize(-5.6)}}

31.7\text{{\color[rgb]{0,0.6,0}\scriptsize(-3.5)}}

72.1\text{{\color[rgb]{0,0.6,0}\scriptsize(-4.2)}}

36.6\text{{\color[rgb]{0,0.6,0}\scriptsize(-5.1)}}

77.1\text{{\color[rgb]{0,0.6,0}\scriptsize(-4.7)}}

Table 1: Average Character Error Rate (CER

\downarrow

) and Word Error Rate (WER

\downarrow

) across all real handwritten datasets for six HTR architectures. Performance is compared against the In-domain upper bound and the Baseline (

\theta_{T}^{\text{syn}}

) zero-shot model. Results are grouped by single analogy and multiple analogy strategies, incorporating uniform and linguistically informed (

\beta_{KL},\beta_{H},\beta_{J}

) priors for zero-shot adaptation. Values in parentheses denote the absolute improvement (

\Delta

) achieved relative to the Baseline.

Figure 3: Zero-shot

\Delta\text{CER}

improvement across all datasets and architectures. We compare single and multi-analogy methods (incorporating linguistic priors) against non-informed baselines (Single

\beta=1

and

\beta=1/N

uniform weighting). Linguistically aware multi-analogy methods achieved the best overall gains.

Figure 4: Distribution of Relative CER decrease (%) achieved using single, unweighted analogies (

\beta=1

) across five target languages (

T

). The largest reduction in error (best transfer) is consistently achieved when the source analogy (

S

) matches the target language (

T

), confirming the strong influence of direct linguistic alignment on the vector’s transferability.

Model	CER oracle	CER heldout	WER oracle	WER heldout
TrOCR(S)	$36.2$	$37.4\text{{\color[rgb]{1,0,0}\scriptsize(+1.2)}}$	$67.9$	$70.0\text{{\color[rgb]{1,0,0}\scriptsize(+2.1)}}$
TrOCR(B)	$31.9$	$33.3\text{{\color[rgb]{1,0,0}\scriptsize(+1.4)}}$	$62.7$	$65.6\text{{\color[rgb]{1,0,0}\scriptsize(+2.9)}}$
TrOCR(L)	$31.3$	$32.8\text{{\color[rgb]{1,0,0}\scriptsize(+1.5)}}$	$62.3$	$66.4\text{{\color[rgb]{1,0,0}\scriptsize(+4.1)}}$
CRNN	$36.6$	$37.0\text{{\color[rgb]{1,0,0}\scriptsize(+0.4)}}$	$71.1$	$71.9\text{{\color[rgb]{1,0,0}\scriptsize(+0.8)}}$
VAN	$30.4$	$31.4\text{{\color[rgb]{1,0,0}\scriptsize(+1.0)}}$	$70.1$	$72.1\text{{\color[rgb]{1,0,0}\scriptsize(+2.0)}}$
HTR-ViT	$34.6$	$35.7\text{{\color[rgb]{1,0,0}\scriptsize(+1.1)}}$	$74.4$	$76.6\text{{\color[rgb]{1,0,0}\scriptsize(+2.2)}}$

Table 2: Heldout and oracle performance for all models averaged about methods and datasets. Performance obtained by heldout selection remain close to their oracle performance, showing the robustness of our approach.

Figure 5: Relative CER improvement across two evaluation scenarios designed for vector bias and generalization. Evaluation on the source domain (

S

) quantifies linguistic bias, while other domain (

Q

) isolates the general language-agnostic component.

Figure 6: Linear Probing results evaluating representation quality (average CER/WER). We compare the Baseline against the best performing Linguistic Aware Single-Analogy and Multi-Analogy merged models, after fine-tuning only the final linear layer.

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Lang.	Period	No. writ	Train	Val	Test	$\|\Sigma\|$
IAM [ 39 ]	En	1999	657	6.4k	976	2.9k	79
Rimes [ 29 ]	Fr	2011	1.3k	10k	1.1k	778	100
LAM [ 12 ]	It	17-18th c.	1	20k	2.5k	3.5k	89
Rodrigo [ 58 ]	Sp	1545	1	20k	1k	5k	115
ICFHR 2016 [ 55 ]	De	15-19th c.	unk.	8.2k	1k	1k	91

Appendix

Table 1: Handwritten document datasets considered, with an indication of the language, historical period, number of writers, number of samples in each partition, and size of the alphabet (

|\Sigma|

Panel of Figure 1 — Figure 1: Language similarity scores between each pair of considered Latin-alphabet languages.

Model	Type	Align.	Vocab	Params	Input size
CRNN [ 50 ]	CRNN	CTC	95	9.6M	128 $\times$ 1024
VAN [ 13 ]	FCN	CTC	95	2.7M	64 $\times$ 1024
HTR-VT [ 33 ]	R 18 +ViT	CTC	95	53.5M	64 $\times$ 512
TrOCR(S) [ 32 ]	ViT+T.Dec	AR	8192	33M	384 $\times$ 384
TrOCR(B) [ 32 ]	ViT+T.Dec	AR	8192	299M	384 $\times$ 384
TrOCR(L) [ 32 ]	ViT+T.Dec	AR	8192	523M	384 $\times$ 384

Appendix

Table 2: Description of HTR architectures considered, including alignment type, vocabulary size, number of parameters, and input image sizes. FCN=Fully Convolutional Network; R=ResNet; T=Transformer; AR=Autoregressive.

Figure 2: Samples from the synthetic datasets used to train the multilingual ancestor model and the synthetic child models for each language, alongside samples from the real datasets to perform the synthetic-to-real analogies.

IAM (en)

Rimes (fr)

LAM (it)

Rodrigo (es)

\text{ICFHR}_{2016}\text{ (de)}

AVG.

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

In-domain

7.7

21.8

4.6

12.5

4.1

13.2

2.1

10.7

6.3

25.2

5.0

16.7

Baseline

\theta_{T}^{syn}

16.4 (+0.0)

39.7 (+0.0)

24.1 (+0.0)

59.1 (+0.0)

46.9 (+0.0)

78.9 (+0.0)

30.3 (+0.0)

76.6 (+0.0)

80.7 (+0.0)

107.8 (+0.0)

39.7 (+0.0)

72.4 (+0.0)

Single analogy

\beta=1

16.3 (-0.1)

40.6 (+0.9)

29.0 (+4.9)

66.5 (+7.4)

36.4 (-10.5)

72.0 (-6.9)

23.8 (-6.5)

70.3 (-6.3)

84.0 (+3.3)

114.8 (+7.0)

37.9 (-1.8)

72.8 (+0.4)

\beta=\beta_{\text{KL}}

12.4 (-4.0)

33.4 (-6.3)

24.8 (+0.7)

61.5 (+2.4)

33.8 (-13.1)

68.2 (-10.7)

23.8 (-6.5)

70.3 (-6.3)

80.3 (-0.4)

107.6 (-0.2)

35.0 (-4.7)

68.2 (-4.2)

Appendix

Table 3: Performance across all real handwritten datasets for TrOCR (S). Values in parentheses are the improvement w.r.t. the Baseline.

	IAM (en)		Rimes (fr)		LAM (it)		Rodrigo (es)		$\text{ICFHR}_{2016}\text{ (de)}$		AVG.
	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$
In-domain	6.3	17.7	3.8	9.6	3.5	11.0	2.2	10.7	6.4	24.8	4.4	14.8
Baseline $\theta_{T}^{syn}$	14.8 (+0.0)	37.7 (+0.0)	22.2 (+0.0)	51.8 (+0.0)	40.3 (+0.0)	75.8 (+0.0)	31.6 (+0.0)	75.7 (+0.0)	79.6 (+0.0)	104.3 (+0.0)	37.7 (+0.0)	69.1 (+0.0)
Single analogy
$\beta=1$	19.5 (+4.7)	45.6 (+7.9)	27.1 (+4.9)	61.6 (+9.8)	32.4 (-7.9)	67.4 (-8.4)	26.5 (-5.1)	72.4 (-3.3)	79.0 (-0.6)	107.5 (+3.2)	36.9 (-0.8)	70.9 (+1.8)
$\beta=\beta_{\text{KL}}$	11.5 (-3.3)	31.8 (-5.9)	19.2 (-3.0)	49.8 (-2.0)	32.2 (-8.1)	69.2 (-6.6)	22.5 (-9.1)	67.2 (-8.5)	79.2 (-0.4)	105.1 (+0.8)	32.9 (-4.8)	64.6 (-4.5)

Appendix

Table 4: Performance across all real handwritten datasets for TrOCR (B). Values in parentheses are the improvement w.r.t. the Baseline.

IAM (en)

Rimes (fr)

LAM (it)

Rodrigo (es)

\text{ICFHR}_{2016}\text{ (de)}

AVG.

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

In-domain

6.7

19.3

3.9

9.6

3.7

11.9

1.8

9.0

5.2

20.5

4.3

14.1

Baseline

\theta_{T}^{syn}

14.0 (+0.0)

35.0 (+0.0)

19.1 (+0.0)

48.3 (+0.0)

40.2 (+0.0)

73.7 (+0.0)

30.2 (+0.0)

76.3 (+0.0)

77.3 (+0.0)

105.7 (+0.0)

36.2 (+0.0)

67.8 (+0.0)

Single analogy

\beta=1

17.0 (+3.0)

42.7 (+7.7)

26.1 (+7.0)

63.0 (+14.7)

33.6 (-6.6)

71.7 (-2.0)

26.3 (-3.9)

76.0 (-0.3)

73.6 (-3.7)

112.1 (+6.4)

35.3 (-0.9)

73.1 (+5.3)

\beta=\beta_{\text{KL}}

12.2 (-1.8)

33.3 (-1.7)

20.0 (+0.9)

53.6 (+5.3)

23.6 (-16.6)

56.5 (-17.2)

27.3 (-2.9)

72.8 (-3.5)

79.1 (+1.8)

106.4 (+0.7)

32.4 (-3.8)

64.5 (-3.3)

Appendix

Table 5: Performance across all real handwritten datasets for TrOCR (L). Values in parentheses are the improvement w.r.t. the Baseline.

	IAM (en)		Rimes (fr)		LAM (it)		Rodrigo (es)		$\text{ICFHR}_{2016}\text{ (de)}$		AVG.
	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$
In-domain	6.2	22.0	4.1	13.8	3.5	12.5	1.0	5.5	6.3	26.1	4.2	16.0
Baseline $\theta_{T}^{syn}$	17.0 (+0.0)	48.4 (+0.0)	23.0 (+0.0)	63.3 (+0.0)	37.3 (+0.0)	78.2 (+0.0)	32.9 (+0.0)	87.0 (+0.0)	83.8 (+0.0)	100.9 (+0.0)	38.8 (+0.0)	75.6 (+0.0)
Single analogy
$\beta=1$	18.3 (+1.3)	50.4 (+2.0)	23.0 (-.0)	63.3 (-.0)	38.2 (+0.9)	73.7 (-4.5)	21.3 (-11.6)	76.7 (-10.3)	78.8 (-5.0)	102.5 (+1.6)	35.9 (-2.9)	73.3 (-2.3)
$\beta=\beta_{\text{KL}}$	15.3 (-1.7)	44.7 (-3.7)	23.0 (-.0)	64.3 (+1.0)	32.3 (-5.0)	71.7 (-6.5)	21.7 (-11.2)	77.2 (-9.8)	84.5 (+0.7)	100.8 (-0.1)	35.4 (-3.4)	71.7 (-3.9)

Appendix

Table 6: Performance across all real handwritten datasets for CRNN. Values in parentheses are the improvement w.r.t. the Baseline.

IAM (en)

Rimes (fr)

LAM (it)

Rodrigo (es)

\text{ICFHR}_{2016}\text{ (de)}

AVG.

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

CER

\downarrow

WER

\downarrow

In-domain

6.7

25.5

5.5

20.4

3.7

13.5

1.7

11.2

9.4

38.5

5.4

21.8

Baseline

\theta_{T}^{syn}

17.6 (+0.0)

52.6 (+0.0)

19.9 (+0.0)

62.9 (+0.0)

33.6 (+0.0)

79.3 (+0.0)

26.8 (+0.0)

84.5 (+0.0)

78.2 (+0.0)

102.0 (+0.0)

35.2 (+0.0)

76.3 (+0.0)

Single analogy

\beta=1

22.6 (+5.0)

62.6 (+10.0)

27.2 (+7.3)

74.1 (+11.2)

28.7 (-4.9)

74.0 (-5.3)

20.5 (-6.3)

75.1 (-9.4)

73.4 (-4.8)

104.3 (+2.3)

34.5 (-0.7)

78.0 (+1.7)

\beta=\beta_{\text{KL}}

14.1 (-3.5)

45.2 (-7.4)

20.5 (+0.6)

65.0 (+2.1)

27.6 (-6.0)

73.3 (-6.0)

19.9 (-6.9)

75.4 (-9.1)

76.3 (-1.9)

101.6 (-0.4)

31.7 (-3.5)

72.1 (-4.2)

Appendix

Table 7: Performance across all real handwritten datasets for VAN. Values in parentheses are the improvement w.r.t. the Baseline.

	IAM (en)		Rimes (fr)		LAM (it)		Rodrigo (es)		$\text{ICFHR}_{2016}\text{ (de)}$		AVG.
	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$
In-domain	7.9	29.6	5.5	20.4	3.6	13.3	2.0	12.9	7.5	33.0	5.3	21.8
Baseline $\theta_{T}^{syn}$	21.9 (+0.0)	62.3 (+0.0)	31.2 (+0.0)	77.2 (+0.0)	45.4 (+0.0)	89.5 (+0.0)	26.2 (+0.0)	79.4 (+0.0)	84.0 (+0.0)	100.4 (+0.0)	41.7 (+0.0)	81.8 (+0.0)
Single analogy
$\beta=1$	28.4 (+6.5)	73.0 (+10.7)	38.3 (+7.1)	86.9 (+9.7)	34.4 (-11.0)	79.7 (-9.8)	23.1 (-3.1)	78.0 (-1.4)	78.8 (-5.2)	101.1 (+0.7)	40.6 (-1.1)	83.7 (+1.9)
$\beta=\beta_{\text{KL}}$	14.9 (-7.0)	49.1 (-13.2)	27.0 (-4.2)	75.5 (-1.7)	36.9 (-8.5)	84.2 (-5.3)	21.5 (-4.7)	76.6 (-2.8)	82.9 (-1.1)	100.3 (-0.1)	36.6 (-5.1)	77.1 (-4.7)

Appendix

Table 8: Performance across all real handwritten datasets for HTR-VIT. Values in parentheses are the improvement w.r.t. the Baseline.

	IAM (en)		Rimes (fr)		LAM (it)		Rodrigo (es)		$\text{ICFHR}_{2016}\text{ (de)}$		AVG.
	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$	CER $\downarrow$	WER $\downarrow$
TrOCR (S)
In-domain	7.7	21.8	4.6	12.5	4.1	13.2	2.1	10.7	6.3	25.2	5.0	16.7
Baseline $\theta_{T}^{syn}$	13.3 (+0.0)	33.1 (+0.0)	13.1 (+0.0)	29.9 (+0.0)	37.5 (+0.0)	66.4 (+0.0)	18.0 (+0.0)	48.5 (+0.0)	70.0 (+0.0)	99.0 (+0.0)	30.4 (+0.0)	55.4 (+0.0)
Single analogy
$\beta=\beta^{*}$	12.9 (-0.4)	31.9 (-1.2)	12.7 (-0.4)	29.0 (-0.9)	23.7 (-13.8)	50.0 (-16.4)	11.8 (-6.2)	35.4 (-13.1)	66.9 (-3.1)	96.5 (-2.5)	25.6 (-4.8)	48.6 (-6.8)

Appendix

Table 9: Linear Probing results obtained with the best performing Linguistic Aware Single-Analogy and Multi-Analogy merged models, after fine-tuning only the final linear layer.

Explore similar work

How Far Can Synthetic Data Take Thai OCR?
Sep 3, 2026Kunat PipatanakulSynthetic-to-Real Domain Adaptation Synthetic Data Generation
Wayu Research · Paxa Labs
Few-shot Writer Adaptation via Multimodal In-Context Learning
Mar 31, 2026Tom Simon, Stephane Nicolas, Pierrick Tranouez +2Optical Character Recognition Few-Shot Learning
LITIS EA4108, University of Rouen Normandy, France · LITIS EA4108, INSA of Rouen Normandy, France
Diffusion-Based Ukrainian Handwritten Text Generation with Cross-Domain Style Transfer
May 26, 2026Andrii Ahitoliev, Pavlo BerezinLatent Diffusion Models Image Style Transfer
Ukrainian Catholic University, Lviv, Ukraine · National University of “Kyiv-Mohyla Academy”, Kyiv, Ukraine

Sep 3, 2026J/K move · Enter open · S save

How Far Can Synthetic Data Take Thai OCR?

Kunat Pipatanakul

Wayu Research · Paxa Labs

Synthetic-to-Real Domain Adaptation Synthetic Data Generation Optical Character Recognition

Open paper AskPDF arXiv

We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the resulting insights to build Wayu-Paxa-OCR-Zero, a Thai OCR model adapted without OCR labels from real Thai document pages. Synthetic data provide exact labels at scale, but "realism" conflates source domain, page context, typography, spatial structure, and glyph variation. We disentangle these factors with a controlled document-reconstruction pipeline and evaluate each variant under page- and crop-level training on printed and handwritten Thai documents. Non-text context has little consistent effect, whereas typeface diversity, two-dimensional structure, and real handwriting glyphs improve transfer; moreover, source-domain matching depends on training granularity, with in-domain reconstruction approaching real printed supervision under page-level training (1.82% versus 1.31% median character error rate) but underperforming out-of-domain reconstruction under crop-level training (15.59% versus 5.52%). Guided by these findings, we adapt the 0.9B-parameter PaddleOCR-VL-1.6 into Wayu-Paxa-OCR-Zero using 45,723 synthetic pages: relative to its base checkpoint, it reduces median character error rate from 6.64% to 1.24% on printed pages and from 74.87% to 20.55% on handwriting and outperforms Typhoon OCR v1 7B on all five evaluation sets, showing that synthetic-only training can be competitive.

Abstract

Explore similar work

How Far Can Synthetic Data Take Thai OCR?

Few-shot Writer Adaptation via Multimodal In-Context Learning

Diffusion-Based Ukrainian Handwritten Text Generation with Cross-Domain Style Transfer