Towards Differentiable Rendering for Sidescan Sonar Imagery
arXiv:2206.07821 · doi:10.1109/AUV53081.2022.9965917
Abstract
Recent advances in differentiable rendering, which allow calculating the gradients of 2D pixel values with respect to 3D object models, can be applied to estimation of the model parameters by gradient-based optimization with only 2D supervision. It is easy to incorporate deep neural networks into such an optimization pipeline, allowing the leveraging of deep learning techniques. This also largely reduces the requirement for collecting and annotating 3D data, which is very difficult for applications, for example when constructing geometry from 2D sensors. In this work, we propose a differentiable renderer for sidescan sonar imagery. We further demonstrate its ability to solve the inverse problem of directly reconstructing a 3D seafloor mesh from only 2D sidescan sonar data.
submitted to 2022 IEEE OES Autonomous Underwater Vehicles (AUV) SYMPOSIUM
References in corpus (5)
- Differentiable Rendering: A Survey
- Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction
- Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
- Neural Network Normal Estimation and Bathymetry Reconstruction from Sidescan Sonar
- High-Resolution Bathymetric Reconstruction From Sidescan Sonar With Deep Neural Networks