End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
This work addresses the challenge of 3D point cloud registration for computer vision applications, representing an incremental improvement over prior methods.
The paper tackles the problem of learning local descriptors for 3D point clouds by proposing an end-to-end framework that integrates multi-view rendering into neural networks, resulting in outperforming existing methods on 3D registration benchmarks.
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.