资源分类
》 资源 》论文》3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

2019-10-22 | |  49 |   40 |   0
Abstract. In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision. Unlike many existing works, we do not require manual annotation of matching point clusters. Instead, we leverage on alignment and attention mechanisms to learn feature correspondences from GPS/INS tagged 3D point clouds without explicitly specifying them. We create training and benchmark outdoor Lidar datasets, and experiments show that 3DFeat-Net obtains state-of-the-art performance on these gravityaligned datasets

上一篇：Generalizing A Person Retrieval Model Hetero- and Homogeneously

下一篇：Video Summarization Using Fully Convolutional Sequence Networks

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to learn...

    The move from hand-designed features to learned...