Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar
This work addresses image formation challenges in SAS for applications like underwater imaging, though it appears incremental as it adapts existing neural rendering techniques to a specific domain.
The paper tackles the problem of limited measurements and hardware constraints in synthetic aperture sonar (SAS) image reconstruction by introducing an analysis-by-synthesis optimization that uses neural rendering to incorporate physics-based constraints and scene priors, resulting in superior reconstructions validated on simulation and experimental data.
Synthetic aperture sonar (SAS) measures a scene from multiple views in order to increase the resolution of reconstructed imagery. Image reconstruction methods for SAS coherently combine measurements to focus acoustic energy onto the scene. However, image formation is typically under-constrained due to a limited number of measurements and bandlimited hardware, which limits the capabilities of existing reconstruction methods. To help meet these challenges, we design an analysis-by-synthesis optimization that leverages recent advances in neural rendering to perform coherent SAS imaging. Our optimization enables us to incorporate physics-based constraints and scene priors into the image formation process. We validate our method on simulation and experimental results captured in both air and water. We demonstrate both quantitatively and qualitatively that our method typically produces superior reconstructions than existing approaches. We share code and data for reproducibility.