BrailleBench：评测并提升 VLM 的盲文识别能力

View PDF HTML (experimental)

Abstract:Despite rapid progress in visual understanding and document transcription, modern vision-language models (VLMs) struggle with a fundamental accessibility task: reading Braille from images. We introduce BrailleBench, a manually curated benchmark of 259 real-world Grade-1 and Grade-2 Braille images. We evaluate proprietary, open-weight, OCR-specialized, and tool-assisted multimodal systems and find that standalone general-purpose models perform poorly at directly transcribing Braille images, whereas tool-assisted systems perform much better. We design a synthetic Braille generation pipeline with diverse layouts and image perturbations. A 2B VLM model trained on our synthetic data reaches 87% exact match on Grade-1 and 61% on Grade-2 BrailleBench, outperforming standalone VLMs and achieving the highest Grade-2 exact match score among the evaluated systems. We further show that high accuracy on synthetic validation data does not guarantee high accuracy on real photographs in our experiments: models trained on prior synthetic data reach up to 96% on their synthetic validation set but at most 3.26% on Grade-1 BrailleBench. Our results identify an accessibility-relevant capability gap in multimodal systems and show that targeted synthetic supervision can improve real-world Braille transcription.

Comments:	22 pages, 8 figures, 16 tables. Code and data: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
Cite as:	arXiv:2610.36195 [cs.CV]
	(or arXiv:2610.36195v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.36195 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Atharva Gawane [view email]
[v1] Mon, 26 Oct 2026 19:32:41 UTC (5,426 KB)