Spatial Acoustic Projection for 3D Imaging Sonar Reconstruction
This addresses the challenge of 3D imaging in underwater or low-visibility environments for applications like robotics or mapping, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of reconstructing 3D surfaces from multi-beam imaging sonar data by integrating intensities from different viewpoints into a 3D grid and using convolutional neural networks to predict signed distances and directions, enabling dense 3D reconstruction from limited viewpoints and evaluated on three real-world datasets.
In this work we present a novel method for reconstructing 3D surfaces using a multi-beam imaging sonar. We integrate the intensities measured by the sonar from different viewpoints for fixed cell positions in a 3D grid. For each cell we integrate a feature vector that holds the mean intensity for a discretized range of viewpoints. Based on the feature vectors and independent sparse range measurements that act as ground truth information, we train convolutional neural networks that allow us to predict the signed distance and direction to the nearest surface for each cell. The predicted signed distances can be projected into a truncated signed distance field (TSDF) along the predicted directions. Utilizing the marching cubes algorithm, a polygon mesh can be rendered from the TSDF. Our method allows a dense 3D reconstruction from a limited set of viewpoints and was evaluated on three real-world datasets.