论文标题
GMF：对应的通用多模式融合框架异常值排斥
GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection
论文作者
论文摘要
拒绝对应异常值可以提高对应质量，这是实现高点云注册精度的关键步骤。当前的最新对应关系排斥方法仅利用对应关系的结构特征。但是，纹理信息对于拒绝人类视力系统中的对应异常值至关重要。在本文中，我们建议一般的多模式融合（GMF）通过利用结构和纹理信息来学会拒绝对应异常值。具体而言，提出了两个基于跨注意的融合层，以从配对图像和从点对应关系中的结构信息中融合纹理信息。此外，我们提出了一个卷积位置编码层，以增强令牌之间的差异并启用编码功能，请注意邻居信息。我们的位置编码层将使跨注意操作同时集成本地和全球信息。在多个数据集（3DMATCH，3DLOMATCH，KITTI）和最新的最新模型（3Dregnet，DGR，DGR，PointDSC）上进行的实验证明，我们的GMF具有广泛的概括能力，并始终提高点云注册精度。此外，几项消融研究表明，提出的GMF对不同损失功能，照明条件和噪声的鲁棒性。该代码可在https://github.com/xiaoshuihuang/gmf上获得。
Rejecting correspondence outliers enables to boost the correspondence quality, which is a critical step in achieving high point cloud registration accuracy. The current state-of-the-art correspondence outlier rejection methods only utilize the structure features of the correspondences. However, texture information is critical to reject the correspondence outliers in our human vision system. In this paper, we propose General Multimodal Fusion (GMF) to learn to reject the correspondence outliers by leveraging both the structure and texture information. Specifically, two cross-attention-based fusion layers are proposed to fuse the texture information from paired images and structure information from point correspondences. Moreover, we propose a convolutional position encoding layer to enhance the difference between Tokens and enable the encoding feature pay attention to neighbor information. Our position encoding layer will make the cross-attention operation integrate both local and global information. Experiments on multiple datasets(3DMatch, 3DLoMatch, KITTI) and recent state-of-the-art models (3DRegNet, DGR, PointDSC) prove that our GMF achieves wide generalization ability and consistently improves the point cloud registration accuracy. Furthermore, several ablation studies demonstrate the robustness of the proposed GMF on different loss functions, lighting conditions and noises.The code is available at https://github.com/XiaoshuiHuang/GMF.
