Salvato in:
Dettagli Bibliografici
Autori principali: Colombo, Antonio, Bianchi, Giovanni
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.18173
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909054100570112
author Colombo, Antonio
Bianchi, Giovanni
author_facet Colombo, Antonio
Bianchi, Giovanni
contents End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask proposals caused by multi-scale variation, arbitrary text shapes, and complex background interference, thereby degrading recognition accuracy. In this paper, we propose a novel Soft Attention Mask Embedding module (SAME) that leverages the global receptive field of Transformer encoders to encode high-level features and compute soft attention weights, which are then hierarchically embedded with predicted masks to generate refined text-boundary-aware masks that effectively suppress background noise. Building upon this module, we present SAME-Net, a robust end-to-end text spotting framework that requires neither character-level annotations nor auxiliary text rectification modules. Since the soft attention mechanism is fully differentiable, recognition loss gradients can be back-propagated through the SAME module to the detection branch, enabling joint optimization of detection and recognition objectives. Extensive experiments on challenging benchmarks demonstrate the effectiveness of our approach: SAME-Net achieves 84.02\% end-to-end H-mean on the arbitrarily-shaped Total-Text dataset, surpassing the previous state-of-the-art GLASS by 1.02\% in full-lexicon accuracy without additional training data, and obtains competitive 83.4\% strong-lexicon results on the multi-oriented ICDAR 2015 dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18173
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
Colombo, Antonio
Bianchi, Giovanni
Computer Vision and Pattern Recognition
End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask proposals caused by multi-scale variation, arbitrary text shapes, and complex background interference, thereby degrading recognition accuracy. In this paper, we propose a novel Soft Attention Mask Embedding module (SAME) that leverages the global receptive field of Transformer encoders to encode high-level features and compute soft attention weights, which are then hierarchically embedded with predicted masks to generate refined text-boundary-aware masks that effectively suppress background noise. Building upon this module, we present SAME-Net, a robust end-to-end text spotting framework that requires neither character-level annotations nor auxiliary text rectification modules. Since the soft attention mechanism is fully differentiable, recognition loss gradients can be back-propagated through the SAME module to the detection branch, enabling joint optimization of detection and recognition objectives. Extensive experiments on challenging benchmarks demonstrate the effectiveness of our approach: SAME-Net achieves 84.02\% end-to-end H-mean on the arbitrarily-shaped Total-Text dataset, surpassing the previous state-of-the-art GLASS by 1.02\% in full-lexicon accuracy without additional training data, and obtains competitive 83.4\% strong-lexicon results on the multi-oriented ICDAR 2015 dataset.
title Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18173