# Who Handles Orientation? Investigating Invariance in Feature Matching

arXiv: https://arxiv.org/abs/2604.11809 · HTML: https://mlsanity.com/paper/2604.11809/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 30 of 43)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [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)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model](https://mlsanity.com/paper/2403.13064/) (2024)
- [SpatialVID: A Large-Scale Video Dataset with Spatial Annotations](https://mlsanity.com/paper/2509.09676/) (2025)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [MegaScenes: Scene-Level View Synthesis at Scale](https://mlsanity.com/paper/2406.11819/) (2024)
- [TILDE: A Temporally Invariant Learned DEtector](https://mlsanity.com/paper/1411.4568/) (2014)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector](https://mlsanity.com/paper/2404.08928/) (2024)

## Built on by (most cited first, 1 of 1)

- [REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching](https://mlsanity.com/paper/2606.24330/) (2026)

## Abstract (arXiv)

Finding matching keypoints between images is a core problem in 3D computer vision. However, modern matchers struggle with large in-plane rotations. A straightforward mitigation is to learn rotation invariance via data augmentation. However, it remains unclear at which stage rotation invariance should be incorporated. In this paper, we study this in the context of a modern sparse matching pipeline. We perform extensive experiments by training on a large collection of 3D vision datasets and evaluating on popular image matching benchmarks. Surprisingly, we find that incorporating rotation invariance already in the descriptor yields similar performance to handling it in the matcher. However, rotation invariance is achieved earlier in the matcher when it is learned in the descriptor, allowing for a faster rotation-invariant matcher. Further, we find that enforcing rotation invariance does not hurt upright performance when trained at scale. Finally, we study the emergence of rotation invariance through scale and find that increasing the training data size substantially improves generalization to rotated images. We release two matchers robust to in-plane rotations that achieve state-of-the-art performance on e.g. multi-modal (WxBS), extreme (HardMatch), and satellite image matching (SatAst). Code is available at https://github.com/davnords/loma.