# DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching

arXiv: https://arxiv.org/abs/2209.10907 · HTML: https://mlsanity.com/paper/2209.10907/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 22 Sep 2022.

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Steerable CNNs](https://mlsanity.com/paper/1612.08498/) (2016)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [Knowledge Adaptation for Efficient Semantic Segmentation](https://mlsanity.com/paper/1903.04688/) (2019)
- [Unpaired Multi-modal Segmentation via Knowledge Distillation](https://mlsanity.com/paper/2001.03111/) (2020)
- [GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs](https://mlsanity.com/paper/1911.05932/) (2019)
- [A case for using rotation invariant features in state of the art feature matchers](https://mlsanity.com/paper/2204.10144/) (2022)
- [RF-Net: An End-to-End Image Matching Network based on Receptive Field](https://mlsanity.com/paper/1906.00604/) (2019)
- [Matchable Image Retrieval by Learning from Surface Reconstruction](https://mlsanity.com/paper/1811.10343/) (2018)
- [RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching](https://mlsanity.com/paper/2103.08573/) (2021)
- [ReF -- Rotation Equivariant Features for Local Feature Matching](https://mlsanity.com/paper/2203.05206/) (2022)

## Built on by (most cited first, 3 of 3)

- [No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views](https://mlsanity.com/paper/2508.01171/) (2025)
- [SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views](https://mlsanity.com/paper/2509.17246/) (2025)
- [From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis](https://mlsanity.com/paper/2603.27455/) (2026)

## Abstract (arXiv)

The performance of local feature descriptors degrades in the presence of large rotation variations. To address this issue, we present an efficient approach to learning rotation invariant descriptors. Specifically, we propose Rotated Kernel Fusion (RKF) which imposes rotations on the convolution kernel to improve the inherent nature of CNN. Since RKF can be processed by the subsequent re-parameterization, no extra computational costs will be introduced in the inference stage. Moreover, we present Multi-oriented Feature Aggregation (MOFA) which aggregates features extracted from multiple rotated versions of the input image and can provide auxiliary knowledge for the training of RKF by leveraging the distillation strategy. We refer to the distilled RKF model as DRKF. Besides the evaluation on a rotation-augmented version of the public dataset HPatches, we also contribute a new dataset named DiverseBEV which is collected during the drone's flight and consists of bird's eye view images with large viewpoint changes and camera rotations. Extensive experiments show that our method can outperform other state-of-the-art techniques when exposed to large rotation variations.