# Image Rotation Angle Estimation: Comparing Circular-Aware Methods

arXiv: https://arxiv.org/abs/2603.25351 · HTML: https://mlsanity.com/paper/2603.25351/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [MambaOut: Do We Really Need Mamba for Vision?](https://mlsanity.com/paper/2405.07992/) (2024)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [An Analysis of SVD for Deep Rotation Estimation](https://mlsanity.com/paper/2006.14616/) (2020)
- [Deep Directional Statistics: Pose Estimation with Uncertainty Quantification](https://mlsanity.com/paper/1805.03430/) (2018)
- [Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection](https://mlsanity.com/paper/2211.06368/) (2022)
- [Rethinking Boundary Discontinuity Problem for Oriented Object Detection](https://mlsanity.com/paper/2305.10061/) (2023)
- [Theoretically Achieving Continuous Representation of Oriented Bounding Boxes](https://mlsanity.com/paper/2402.18975/) (2024)
- [Deep Rotation Correction without Angle Prior](https://mlsanity.com/paper/2207.03054/) (2022)
- [Deep Image Orientation Angle Detection](https://mlsanity.com/paper/2007.06709/) (2020)
- [Automatic Photo Orientation Detection with Convolutional Neural Networks](https://mlsanity.com/paper/2305.10319/) (2023)

## Abstract (arXiv)

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 1.23deg (mean across five independent runs) on the DRC-D dataset, while the circular Gaussian distribution with MambaOut Base achieves a virtually identical 1.24deg with greater robustness across backbones. Training and evaluating our top-performing method-architecture combinations on COCO 2014, the best configuration reaches 3.71deg MAE, improving substantially over prior work, with further improvement to 2.84deg on the larger COCO 2017 dataset.