Computing a Characteristic Orientation for Rotation-Independent Image Analysis

• URL: http://arxiv.org/abs/2602.20930v1
• Date: Tue, 24 Feb 2026 14:08:12 GMT
• Title: Computing a Characteristic Orientation for Rotation-Independent Image Analysis
• Authors: Cristian Valero-Abundio, Emilio Sansano-Sansano, Raúl Montoliu, Marina Martínez García,
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Handling geometric transformations, particularly rotations, remains a challenge in deep learning for computer vision. Standard neural networks lack inherent rotation invariance and typically rely on data augmentation or architectural modifications to improve robustness. Although effective, these approaches increase computational demands, require specialised implementations, or alter network structures, limiting their applicability. This paper introduces General Intensity Direction (GID), a preprocessing method that improves rotation robustness without modifying the network architecture. The method estimates a global orientation for each image and aligns it to a canonical reference frame, allowing standard models to process inputs more consistently across different rotations. Unlike moment-based approaches that extract invariant descriptors, this method directly transforms the image while preserving spatial structure, making it compatible with convolutional networks. Experimental evaluation on the rotated MNIST dataset shows that the proposed method achieves higher accuracy than state-of-the-art rotation-invariant architectures. Additional experiments on the CIFAR-10 dataset, confirm that the method remains effective under more complex conditions.

Related papers

• 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)
• Rotation-Equivariant Self-Supervised Method in Image Denoising [46.44312175792672]
  This paper introduces high-accuracy rotation equivariant convolution to self-supervised image denoising.<n>To the best of our knowledge, this is the first time that rotation equivariant image prior is introduced to self-supervised image denoising.<n>To further improve the performance, we design a new mask mechanism to fusion the output of rotation equivariant network and vanilla CNN-based network.
  arXiv  Detail & Related papers  (2025-05-26T07:32:52Z)
• Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution [52.55429225242423]
  We propose a novel framework for Burst Image Super-Resolution (BISR), featuring an equivariant convolution-based alignment.<n>This enables the alignment transformation to be learned via explicit supervision in the image domain and easily applied in the feature domain.<n>Experiments on BISR benchmarks show the superior performance of our approach in both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2025-03-11T11:13:10Z)
• PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation [10.748412559871621]
  This paper introduces a universal convolution-group framework aimed at more fully utilizing orientation information.<n>We then mathematically design a padding-based rotation equivariant convolution mode (PreCM)<n>To quantitatively assess the impact of image rotation in semantic segmentation tasks, we also propose a new evaluation metric, Rotation Difference (RD)
  arXiv  Detail & Related papers  (2024-11-03T16:26:55Z)
• Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1 [51.404644401997736]
  We propose a complete framework to remove speckle in polarimetric SAR images using a convolutional neural network. Experiments show that the proposed approach offers exceptional results in both speckle reduction and resolution preservation.
  arXiv  Detail & Related papers  (2024-08-28T10:07:17Z)
• Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration [62.41329042683779]
  We propose a high-accuracy rotation equivariant proximal network that embeds rotation symmetry priors into the deep unfolding framework. This study makes efforts to suggest a high-accuracy rotation equivariant proximal network that effectively embeds rotation symmetry priors into the deep unfolding framework.
  arXiv  Detail & Related papers  (2023-12-25T11:53:06Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• ReF -- Rotation Equivariant Features for Local Feature Matching [30.459559206664427]
  We propose an alternative, complementary approach that centers on inducing bias in the model architecture itself to generate rotation-specific' features. We demonstrate that this high performance, rotation-specific coverage from the steerable CNNs can be expanded to all rotation angles. We present a detailed analysis of the performance effects of ensembling, robust estimation, network architecture variations, and the use of rotation priors.
  arXiv  Detail & Related papers  (2022-03-10T07:36:09Z)
• Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration [77.99182201815763]
  Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. We propose a novel monomial selection algorithm based on pruning methods to allow an application to more complex problems. We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets.
  arXiv  Detail & Related papers  (2022-02-08T16:16:11Z)
• SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting [2.624902795082451]
  Unwrapping an image into its polar coordinates provides a more explicit representation to train a convolutional architecture. We show that this preprocessing step significantly improves prediction results by standardising the scene representation. This transformation magnifies the area surrounding the centre of the rotation, leading to more accurate short-term irradiance predictions.
  arXiv  Detail & Related papers  (2021-11-29T12:58:57Z)
• Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis [11.568329857588099]
  We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks. We show that consistent increase of performances can be achieved when using the proposed framework.
  arXiv  Detail & Related papers  (2020-02-20T13:44:29Z)

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.