MS2DG-Net: Progressive Correspondence Learning via Multiple Sparse Semantics Dynamic Graph

Luanyuan Dai, Yizhang Liu, Jiayi Ma, Lifang Wei, Taotao Lai, Changcai Yang, Riqing Chen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 8973-8982

Abstract


Establishing superior-quality correspondences in an image pair is pivotal to many subsequent computer vision tasks. Using Euclidean distance between correspondences to find neighbors and extract local information is a common strategy in previous works. However, most such works ignore similar sparse semantics information between two given images and cannot capture local topology among correspondences well. Therefore, to deal with the above problems, Multiple Sparse Semantics Dynamic Graph Network (MS^ 2 DG-Net) is proposed, in this paper, to predict probabilities of correspondences as inliers and recover camera poses. MS^ 2 DG-Net dynamically builds sparse semantics graphs based on sparse semantics similarity between two given images, to capture local topology among correspondences, while maintaining permutation-equivariant. Extensive experiments prove that MS^ 2 DG-Net outperforms state-of-the-art methods in outlier removal and camera pose estimation tasks on the public datasets with heavy outliers. Source code:https://github.com/changcaiyang/MS2DG-Net

Related Material


[pdf]
[bibtex]
@InProceedings{Dai_2022_CVPR, author = {Dai, Luanyuan and Liu, Yizhang and Ma, Jiayi and Wei, Lifang and Lai, Taotao and Yang, Changcai and Chen, Riqing}, title = {MS2DG-Net: Progressive Correspondence Learning via Multiple Sparse Semantics Dynamic Graph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {8973-8982} }