# Single View Seafloor Recovery from Imaging Sonar via Differentiable Rendering

arXiv: https://arxiv.org/abs/2605.24195 · HTML: https://mlsanity.com/paper/2605.24195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 9 of 9)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Implicit Surface Reconstruction using Imaging Sonar](https://mlsanity.com/paper/2209.08221/) (2022)
- [Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar](https://mlsanity.com/paper/2306.09909/) (2023)
- [AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusion](https://mlsanity.com/paper/2402.03309/) (2024)
- [Bathymetric Surveying with Imaging Sonar Using Neural Volume Rendering](https://mlsanity.com/paper/2404.14819/) (2024)
- [2D Forward Looking Sonar Simulation with Ground Echo Modeling](https://mlsanity.com/paper/2304.08146/) (2023)
- [Towards Differentiable Rendering for Sidescan Sonar Imagery](https://mlsanity.com/paper/2206.07821/) (2022)
- [Neural Shape-from-Shading for Survey-Scale Self-Consistent Bathymetry from Sidescan](https://mlsanity.com/paper/2206.09276/) (2022)
- [Synthetic Enclosed Echoes: A New Dataset to Mitigate the Gap Between Simulated and Real-World Sonar Data](https://mlsanity.com/paper/2505.15465/) (2025)

## Abstract (arXiv)

Sonar is often the only modality suitable for high-resolution imaging underwater due to light attenuation and turbidity. Forward-looking imaging sonar provides measurements over range and horizontal angle but collapses vertical structure into a flat image, creating ambiguities that make 3D recovery challenging. A common use case for imaging sonar is underwater terrain mapping (bathymetry), yet current methods require many views, expensive multi-sensor setups, or significant training data, which limits use and adaptability to new environments. We present a training-free method that recovers bathymetry from a single sonar image in under 30 seconds via differentiable rendering, conditioned on a known seafloor tilt. To our knowledge, this is the first differentiable rendering approach for single-view height recovery in sonar. Our method implements differentiable sonar ray tracing and optimizes an explicit height field to reproduce the target image. On synthetic datasets, our approach outperforms a supervised CNN under distribution shift and remains close on rough terrain, while the CNN wins in-distribution. By modeling physically grounded priors of the sonar process, our method adapts across sensor configurations and environments without training data.