# RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching

arXiv: https://arxiv.org/abs/2103.08573 · HTML: https://mlsanity.com/paper/2103.08573/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 15 Mar 2021.

## Builds on (most cited first, 23 of 23)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [High Quality Monocular Depth Estimation via Transfer Learning](https://mlsanity.com/paper/1812.11941/) (2018)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations](https://mlsanity.com/paper/1809.04766/) (2018)
- [MonoLayout: Amodal scene layout from a single image](https://mlsanity.com/paper/2002.08394/) (2020)
- [A comprehensive, application-oriented study of catastrophic forgetting in DNNs](https://mlsanity.com/paper/1905.08101/) (2019)
- [LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics](https://mlsanity.com/paper/1804.05526/) (2018)
- [A Geometric Approach to Obtain a Bird's Eye View from an Image](https://mlsanity.com/paper/1905.02231/) (2019)
- [D2D: Keypoint Extraction with Describe to Detect Approach](https://mlsanity.com/paper/2005.13605/) (2020)
- [S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching](https://mlsanity.com/paper/2004.01673/) (2020)
- [RF-Net: An End-to-End Image Matching Network based on Receptive Field](https://mlsanity.com/paper/1906.00604/) (2019)
- [Single-Image Depth Prediction Makes Feature Matching Easier](https://mlsanity.com/paper/2008.09497/) (2020)
- [CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers](https://mlsanity.com/paper/2007.10588/) (2020)
- [The Right (Angled) Perspective: Improving the Understanding of Road Scenes Using Boosted Inverse Perspective Mapping](https://mlsanity.com/paper/1812.00913/) (2018)
- [Topological Mapping for Manhattan-like Repetitive Environments](https://mlsanity.com/paper/2002.06575/) (2020)
- [Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments](https://mlsanity.com/paper/2010.01421/) (2020)
- [Simultaneous Localization and Mapping (SLAM) using RTAB-MAP](https://mlsanity.com/paper/1809.02989/) (2018)

## Built on by (most cited first, 19 of 19)

- [PATS: Patch Area Transportation with Subdivision for Local Feature Matching](https://mlsanity.com/paper/2303.07700/) (2023)
- [Adaptive Assignment for Geometry Aware Local Feature Matching](https://mlsanity.com/paper/2207.08427/) (2022)
- [Decoupling Makes Weakly Supervised Local Feature Better](https://mlsanity.com/paper/2201.02861/) (2022)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [VPAIR -- Aerial Visual Place Recognition and Localization in Large-scale Outdoor Environments](https://mlsanity.com/paper/2205.11567/) (2022)
- [FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network](https://mlsanity.com/paper/2211.15069/) (2022)
- [Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement](https://mlsanity.com/paper/2303.08438/) (2023)
- [Structured Epipolar Matcher for Local Feature Matching](https://mlsanity.com/paper/2303.16646/) (2023)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods](https://mlsanity.com/paper/2108.08179/) (2021)
- [DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching](https://mlsanity.com/paper/2209.10907/) (2022)
- [Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images](https://mlsanity.com/paper/2306.01938/) (2023)
- [ReF -- Rotation Equivariant Features for Local Feature Matching](https://mlsanity.com/paper/2203.05206/) (2022)
- [Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras](https://mlsanity.com/paper/2409.18673/) (2024)
- [CM-Bench: A Comprehensive Cross-Modal Feature Matching Benchmark Bridging Visible and Infrared Images](https://mlsanity.com/paper/2603.12690/) (2026)
- [SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms](https://mlsanity.com/paper/2208.09896/) (2022)
- [GMatch: A Lightweight, Geometry-Constrained Keypoint Matcher for Zero-Shot 6DoF Pose Estimation in Robotic Grasp Tasks](https://mlsanity.com/paper/2505.16144/) (2025)
- [Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinement](https://mlsanity.com/paper/2608.15251/) (2026)

## Abstract (arXiv)

The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme. Past research in this area has typically focused on one of two approaches to this challenge: the use of projections into spaces more suitable for feature matching under extreme viewpoint changes, and attempting to learn features that are inherently more robust to viewpoint change. In this paper, we present a novel framework that combines learning of invariant descriptors through data augmentation and orthographic viewpoint projection. We propose rotation-robust local descriptors, learnt through training data augmentation based on rotation homographies, and a correspondence ensemble technique that combines vanilla feature correspondences with those obtained through rotation-robust features. Using a range of benchmark datasets as well as contributing a new bespoke dataset for this research domain, we evaluate the effectiveness of the proposed approach on key tasks including pose estimation and visual place recognition. Our system outperforms a range of baseline and state-of-the-art techniques, including enabling higher levels of place recognition precision across opposing place viewpoints and achieves practically-useful performance levels even under extreme viewpoint changes.