Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition

• URL: http://arxiv.org/abs/2608.10684v1
• Date: Tue, 11 Aug 2026 09:06:46 GMT
• Title: Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition
• Abstract summary: Multi-oriented text is a major challenge for scene text recognition.<n>Existing rotation-aware methods explicitly estimate text orientation.<n>We incorporate rotation invariance into the STR framework to address these limitations.
• Score: 49.665177053925184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-oriented text is ubiquitous in real-world scenes and remains a major challenge for scene text recognition (STR). Existing rotation-aware methods explicitly estimate text orientation. However, due to the lack of theoretical guarantees, they are prone to error accumulation, increased computational cost, and strong reliance on data. In this work, we incorporate rotation invariance into the STR framework to address these limitations. Specifically, we adopt an encoder-decoder architecture, embedding rotation equivariance in the encoder and rotation invariance in the decoder to construct a fully rotation-invariant network. On the decoder side, we first identify and prove the rotation-invariant property of the cross-attention mechanism and use it to formulate a rotation-invariant text decoder that maps visual features to output text in a rotation-invariant manner. On the encoder side, we propose a rotation-equivariant local-global extraction network that integrates deep equivariant convolutions with self-attention, enabling rotation-equivariant feature extraction while modeling inter-character dependencies and preserving fine-grained visual details. By integrating the encoder and decoder, we obtain an end-to-end Rotation-Invariant Scene Text Recognition network (RISTER). RISTER provides rotation invariance with theoretical guarantees, enhancing robustness on multi-oriented samples without introducing additional inference computation or relying on data-driven orientation correction. Experiments show that RISTER achieves state-of-the-art performance on both standard and multi-oriented benchmarks, surpassing the second-best model by 4.0 percent in accuracy on the general multi-oriented dataset.

Related papers

• REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching [9.492474203638965]
  Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge.<n>Redi-Match is an efficient framework driven by a novel Rotation-Equivariant Distillation (REDI) paradigm.<n>It achieves a 13.89% absolute pose accuracy improvement on the SatAst dataset while operating 1.9x faster than the current SOTA.
  arXiv  Detail & Related papers  (2026-06-23T09:05:20Z)
• Computing a Characteristic Orientation for Rotation-Independent Image Analysis [0.0]
  General Intensity Direction (GID) is a preprocessing method that improves rotation robustness without modifying the network architecture.<n>It transforms the image while preserving spatial structure, making it compatible with convolutional networks.<n> Experimental evaluation on the rotated MNIST dataset shows that the proposed method achieves higher accuracy than state-of-the-art rotation-invariant architectures.
  arXiv  Detail & Related papers  (2026-02-24T14:08:12Z)
• Selective Rotary Position Embedding [84.22998043041198]
  We introduce textitSelective RoPE, an textitinput-dependent rotary embedding mechanism.<n>We show that softmax attention already performs a hidden form of these rotations on query-key pairs.<n>We validate our method by equipping gated transformers with textitSelective RoPE, demonstrating that its input-dependent rotations improve performance in language modeling.
  arXiv  Detail & Related papers  (2025-11-21T16:50:00Z)
• Rotation Equivariant Arbitrary-scale Image Super-Resolution [62.41329042683779]
  The arbitrary-scale image super-resolution (ASISR) aims to achieve arbitrary-scale high-resolution recoveries from a low-resolution input image.<n>We make efforts to construct a rotation equivariant ASISR method in this study.
  arXiv  Detail & Related papers  (2025-08-07T08:51:03Z)
• RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning [24.532566288697684]
  Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data.<n>These methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational variations.<n>We propose a novel Rotation-Invariant Masked AutoEncoders (RI-MAE) to address two major challenges.
  arXiv  Detail & Related papers  (2024-08-31T05:17:55Z)
• PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration [8.668461141536383]
  Learning rotation-invariant distinctive features is a fundamental requirement for point cloud registration. Existing methods often use rotation-sensitive networks to extract features, while employing rotation augmentation to learn an approximate invariant mapping rudely. We propose a novel position-aware rotation-equivariant network, for efficient, light-weighted, and robust registration.
  arXiv  Detail & Related papers  (2024-07-14T10:26:38Z)
• Locality-Aware Generalizable Implicit Neural Representation [54.93702310461174]
  Generalizable implicit neural representation (INR) enables a single continuous function to represent multiple data instances. We propose a novel framework for generalizable INR that combines a transformer encoder with a locality-aware INR decoder. Our framework significantly outperforms previous generalizable INRs and validates the usefulness of the locality-aware latents for downstream tasks.
  arXiv  Detail & Related papers  (2023-10-09T11:26:58Z)
• Rotation-Invariant Transformer for Point Cloud Matching [42.5714375149213]
  We introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task. We propose a global transformer with rotation-invariant cross-frame spatial awareness learned by the self-attention mechanism. RoITr surpasses the existing methods by at least 13 and 5 percentage points in terms of Inlier Ratio and Registration Recall.
  arXiv  Detail & Related papers  (2023-03-14T20:55:27Z)
• SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement [118.20816888815658]
  We propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded Selective Position variant' procedure relies on an attention mechanism that can effectively attend to the underlying rotation condition of the input. We demonstrate the merits of the SPE-Net and the associated hypothesis on four benchmarks, showing evident improvements on both rotated and unrotated test data over SOTA methods.
  arXiv  Detail & Related papers  (2022-11-15T15:59:09Z)
• Rethinking Text Line Recognition Models [57.47147190119394]
  We consider two decoder families (Connectionist Temporal Classification and Transformer) and three encoder modules (Bidirectional LSTMs, Self-Attention, and GRCLs) We compare their accuracy and performance on widely used public datasets of scene and handwritten text. Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length.
  arXiv  Detail & Related papers  (2021-04-15T21:43:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.