Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network

by   Zizhuo Li, et al.

Accurately matching local features between a pair of images is a challenging computer vision task. Previous studies typically use attention based graph neural networks (GNNs) with fully-connected graphs over keypoints within/across images for visual and geometric information reasoning. However, in the context of feature matching, considerable keypoints are non-repeatable due to occlusion and failure of the detector, and thus irrelevant for message passing. The connectivity with non-repeatable keypoints not only introduces redundancy, resulting in limited efficiency, but also interferes with the representation aggregation process, leading to limited accuracy. Targeting towards high accuracy and efficiency, we propose MaKeGNN, a sparse attention-based GNN architecture which bypasses non-repeatable keypoints and leverages matchable ones to guide compact and meaningful message passing. More specifically, our Bilateral Context-Aware Sampling Module first dynamically samples two small sets of well-distributed keypoints with high matchability scores from the image pair. Then, our Matchable Keypoint-Assisted Context Aggregation Module regards sampled informative keypoints as message bottlenecks and thus constrains each keypoint only to retrieve favorable contextual information from intra- and inter- matchable keypoints, evading the interference of irrelevant and redundant connectivity with non-repeatable ones. Furthermore, considering the potential noise in initial keypoints and sampled matchable ones, the MKACA module adopts a matchability-guided attentional aggregation operation for purer data-dependent context propagation. By these means, we achieve the state-of-the-art performance on relative camera estimation, fundamental matrix estimation, and visual localization, while significantly reducing computational and memory complexity compared to typical attentional GNNs.


page 1

page 3

page 7

page 8

page 11


Learning to Match Features with Seeded Graph Matching Network

Matching local features across images is a fundamental problem in comput...

Graph Joint Attention Networks

Graph attention networks (GATs) have been recognized as powerful tools f...

ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching

Graph Neural Networks (GNNs) with attention have been successfully appli...

Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs

We present the Sequential Aggregation and Rematerialization (SAR) scheme...

VersaGNN: a Versatile accelerator for Graph neural networks

Graph Neural Network (GNN) is a promising approach for analyzing graph-s...

CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation

Commonsense knowledge is crucial to many natural language processing tas...

ContextDesc: Local Descriptor Augmentation with Cross-Modality Context

Most existing studies on learning local features focus on the patch-base...

Please sign up or login with your details

Forgot password? Click here to reset