# RF-Net: An End-to-End Image Matching Network based on Receptive Field

Source: [RF-Net: An End-to-End Image Matching Network based on Receptive Field](<https://www.sota2.com/research/paper/68fa65d61e209131cea0c964>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:36:37.771Z

Authors: Xuelun Shen, Cheng Wang, Xin Li, Zenglei Yu, Jonathan Li, Chenglu Wen, Ming Cheng, Zijian He

Published: 2019-06-03T07:11:48.000Z

## Abstract

This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images. Building end-to-end trainable matching framework is desirable and challenging. The very recent approach, LF-Net, successfully embeds the entire feature extraction pipeline into a jointly trainable pipeline, and produces the state-of-the-art matching results. This paper introduces two modifications to the structure of LF-Net. First, we propose to construct receptive feature maps, which lead to more effective keypoint detection. Second, we introduce a general loss function term, neighbor mask, to facilitate training patch selection. This results in improved stability in descriptor training. We trained RF-Net on the open dataset HPatches, and compared it with other methods on multiple benchmark datasets. Experiments show that RF-Net outperforms existing state-of-the-art methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Local Feature Matching on HPatches (all)](<https://www.sota2.com/research/sota/local-feature-matching-on-hpatches-all.md>): Local Feature Matching; HPatches (all); MMA@5px: 59.08.

- [Local Feature Matching on HPatches (viewpoint)](<https://www.sota2.com/research/sota/local-feature-matching-on-hpatches-viewpoint.md>): Local Feature Matching; HPatches (viewpoint); MMA (5px): 56.62.

- [Local Feature Matching on HPatches illumination](<https://www.sota2.com/research/sota/local-feature-matching-on-hpatches-illumination.md>): Local Feature Matching; HPatches illumination; MMA@5px: 61.63.

- [Camera Pose Estimation on MVS](<https://www.sota2.com/research/sota/camera-pose-estimation-on-mvs.md>): Camera pose estimation; MVS; mAA @ 20 deg: 10.

- [Local Descriptor Matching on Roto-360 1.0 (test)](<https://www.sota2.com/research/sota/local-descriptor-matching-on-roto-360-1-0-test.md>): Local Descriptor Matching; Roto-360 1.0 (test); MMA @10px: 15.64.

- [Image Captioning on MS COCO Karpathy (test)](<https://www.sota2.com/research/sota/image-captioning-on-ms-coco-karpathy-test.md>): Image Captioning; MS COCO Karpathy (test); CIDEr: 1.219.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.00604>)

[PDF](<https://arxiv.org/pdf/1906.00604.pdf>)