期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 3236-3245出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.00325
关键词
-
资金
- General Research Fund (GRF) of the Research Grant Council of Hong Kong [17210718]
Motion coherence is crucial for distinguishing true correspondences, and the proposed LMCNet combines global and local coherence to robustly detect inlier correspondences, outperforming existing methods in relative camera pose estimation and correspondences pruning in dynamic scenes.
Motion coherence is an important clue for distinguishing true correspondences from false ones. Modeling motion coherence on sparse putative correspondences is challenging due to their sparsity and uneven distributions. Existing works on motion coherence are sensitive to parameter settings and have difficulty in dealing with complex motion patterns. In this paper, we introduce a network called Laplacian Motion Coherence Network (LMCNet) to learn motion coherence property for correspondence pruning. We propose a novel formulation of fitting coherent motions with a smooth function on a graph of correspondences and show that this formulation allows a closed-form solution by graph Laplacian. This closed-form solution enables us to design a differentiable layer in a learning framework to capture global motion coherence from putative correspondences. The global motion coherence is further combined with local coherence extracted by another local layer to robustly detect inlier correspondences. Experiments demonstrate that LMCNet has superior performances to the state of the art in relative camera pose estimation and correspondences pruning of dynamic scenes(1).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据