IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration

The existing state-of-the-art point descriptor relies on structure information only, which omits the texture information. However, texture information is crucial for our humans to distinguish a scene part. Moreover, the current learning-based point descriptors are all black boxes which are unclear how the original points contribute to the final descriptor. This paper proposes a new multimodal fusion method to generate a point cloud registration descriptor by considering structure and texture information. Specifically, a novel attention-fusion module is designed to extract the weighted texture information for descriptor extraction. In addition, we propose an interpretable module to explain our neural network by visually showing the original points contributing to the final descriptor. We use the descriptor's channel value as the loss to backpropagate to the target layer and consider the gradient as the significance of this point to the final descriptor. This paper moves one step further to explainable deep learning in the registration task. Comprehensive experiments on 3DMatch, 3DLoMatch and KITTI demonstrate that the multimodal fusion descriptor achieves state-of-the-art accuracy and improves the descriptor's distinctiveness. We also demonstrate our interpretable module in explaining the registration descriptor extraction.