Image Rotation Angle Estimation: Comparing Circular-Aware Methods

• URL: http://arxiv.org/abs/2603.25351v1
• Date: Thu, 26 Mar 2026 11:57:28 GMT
• Title: Image Rotation Angle Estimation: Comparing Circular-Aware Methods
• Abstract summary: We present a comprehensive study of five circular-aware methods for global orientation estimation.<n>Direct angle regression with circular loss, classification via angular binning, unit-vector regression, phase-shifting coder, and circular Gaussian distribution are studied.<n>We adapt these methods across sixteen modern architectures by adapting their output heads for rotation-specific predictions.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic image rotation estimation is a key preprocessing step in many vision pipelines. This task is challenging because angles have circular topology, creating boundary discontinuities that hinder standard regression methods. We present a comprehensive study of five circular-aware methods for global orientation estimation: direct angle regression with circular loss, classification via angular binning, unit-vector regression, phase-shifting coder, and circular Gaussian distribution. Using transfer learning from ImageNet-pretrained models, we systematically evaluate these methods across sixteen modern architectures by adapting their output heads for rotation-specific predictions. Our results show that probabilistic methods, particularly the circular Gaussian distribution, are the most robust across architectures, while classification achieves the best accuracy on well-matched backbones but suffers training instabilities on others. The best configuration (classification with EfficientViT-B3) achieves a mean absolute error (MAE) of 1.23° (mean across five independent runs) on the DRC-D dataset, while the circular Gaussian distribution with MambaOut Base achieves a virtually identical 1.24° with greater robustness across backbones. Training and evaluating our top-performing method-architecture combinations on COCO 2014, the best configuration reaches 3.71° MAE, improving substantially over prior work, with further improvement to 2.84° on the larger COCO 2017 dataset.

Related papers

• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Angle-I2P: Angle-Consistent-Aware Hierarchical Attention for Cross-Modality Outlier Rejection [20.302748104301525]
  Image-to-point-cloud registration (I2P) is a fundamental task in robotic applications such as manipulation,grasping, and localization.<n>We propose Angle-I2P, an outlier rejection network that leverages angle-consistent geometric constraints and hierarchical attention.<n>We show that our method achieves state-of-the-art performance on the 7Scenes, RGBD Scenes V2, and a self-collected dataset.
  arXiv  Detail & Related papers  (2026-05-06T06:41:56Z)
• Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation [109.13471554184554]
  We reformulate dataset distillation as an Optimal Transport (OT) distance minimization problem.<n>OT offers a geometrically faithful framework for distribution matching.<n>Our method consistently outperforms state-of-the-art approaches in an efficient manner.
  arXiv  Detail & Related papers  (2025-11-29T04:04:05Z)
• GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting [16.179607149692398]
  We present GaussianCross, a novel cross-modal self-supervised 3D representation learning architecture.<n>GaussianCross seamlessly converts scale-inconsistent 3D point clouds into a unified cuboid-normalized Gaussian representation.<n>It achieves superior performance through linear probing (0.1% parameters) and limited data training (1% of scenes) compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-04T08:12:44Z)
• 3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation [30.625439879741847]
  We present a toolkit for a Modularized 3D Face reconstruction Benchmark (M3DFB)<n>The fundamental components of error are segregated and interchangeable, allowing one to quantify the effect of each.<n>We propose a new component, namely correction, and present a computationally efficient approach that penalizes for mesh topology inconsistency.
  arXiv  Detail & Related papers  (2025-05-23T15:28:43Z)
• E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network [47.77270862087191]
  We propose E3-Net to achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work. Our method achieves superior results on both synthetic and real-world datasets, and outperforms current state-of-the-art techniques by a substantial margin.
  arXiv  Detail & Related papers  (2024-06-01T07:53:36Z)
• Multiway Point Cloud Mosaicking with Diffusion and Global Optimization [74.3802812773891]
  We introduce a novel framework for multiway point cloud mosaicking (named Wednesday) At the core of our approach is ODIN, a learned pairwise registration algorithm that identifies overlaps and refines attention scores. Tested on four diverse, large-scale datasets, our method state-of-the-art pairwise and rotation registration results by a large margin on all benchmarks.
  arXiv  Detail & Related papers  (2024-03-30T17:29:13Z)
• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models [4.374569172244273]
  We propose to use control for learned models to recover from distribution shifts online. Our method applies a sequence of semantic-preserving transformations to bring the shifted data closer in distribution to the training set. We show that our method generalizes to composites of shifts from the ImageNet-C benchmark, achieving improvements in average accuracy of up to 9.81%.
  arXiv  Detail & Related papers  (2023-02-20T22:06:26Z)
• RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging [62.315673415889314]
  This paper proposes a deep recurrent Rotation Averaging Graph (RAGO) for Multiple Rotation Averaging (MRA) Our framework is a real-time learning-to-optimize rotation averaging graph with a tiny size deployed for real-world applications.
  arXiv  Detail & Related papers  (2022-12-14T13:19:40Z)
• ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation [89.47574181669903]
  In this study, we show that the rotation robustness of point cloud classifiers can also be acquired via adversarial training. Specifically, our proposed framework named ART-Point regards the rotation of the point cloud as an attack. We propose a fast one-step optimization to efficiently reach the final robust model.
  arXiv  Detail & Related papers  (2022-03-08T07:20:16Z)
• 6D Rotation Representation For Unconstrained Head Pose Estimation [2.1485350418225244]
  We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data. This way, our method can learn the full rotation appearance which is contrary to previous approaches that restrict the pose prediction to a narrow-angle. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20%.
  arXiv  Detail & Related papers  (2022-02-25T08:41:13Z)
• Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
  We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-02-29T06:24:55Z)

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.