Single View Seafloor Recovery from Imaging Sonar via Differentiable Rendering

• URL: http://arxiv.org/abs/2605.24195v1
• Date: Fri, 22 May 2026 20:36:49 GMT
• Title: Single View Seafloor Recovery from Imaging Sonar via Differentiable Rendering
• Abstract summary: We present a training-free method that recovers bathymetry from a single sonar image in under 30 seconds.<n>To our knowledge, this is the first differentiable rendering approach for single-view height recovery in sonar.
• Score: 12.051446549851844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• ISOPoT: Imaging Sonar Odometry by Point Tracking [34.99229313882639]
  We introduce ISOPoT, an imaging sonar odometry method based on modern point tracking techniques.<n>We propose a sonar odometry pipeline that uses multi-frame point tracks as its primary correspondence representation.<n>Our results show that ISOPoT outperforms previous state-of-the-art methods consistently in both sonar-only scenarios and in multi-sensor settings.
  arXiv  Detail & Related papers  (2026-06-22T08:18:39Z)
• BALTIC: A Benchmark and Cross-Domain Strategy for 3D Reconstruction Across Air and Underwater Domains Under Varying Illumination [6.8920172327690175]
  We introduce BALTIC, a benchmark designed to evaluate modern 3D reconstruction methods under variations in medium and lighting.<n>The benchmark comprises 13 datasets spanning two media (air and water) and three lighting conditions (ambient, artificial, and mixed)<n>We investigate cross-domain reconstruction by augmenting underwater image sequences with a small number of in-air views captured under similar lighting conditions.
  arXiv  Detail & Related papers  (2026-04-21T06:32:07Z)
• Unblur-SLAM: Dense Neural SLAM for Blurry Inputs [68.94602568657164]
  Un-SLAM is a novel pipeline for sharp 3D reconstruction from blurred image inputs.<n>We demonstrate state-of-the-art performance in the presence of both motion blur and defocus blur.<n>Experiments on several real-world datasets demonstrate consistent improvements in both pose estimation and sharp reconstruction results.
  arXiv  Detail & Related papers  (2026-03-26T14:29:47Z)
• Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching [80.57282092735991]
  We propose an accurate and interpretable fine-grained cross-view localization method.<n>It estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image.<n> Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation.
  arXiv  Detail & Related papers  (2025-09-11T18:52:16Z)
• Single-Step Latent Diffusion for Underwater Image Restoration [25.229678050715496]
  Underwater image restoration algorithms seek to restore the color, contrast, and appearance of a scene that is imaged underwater.<n>They are a critical tool in applications ranging from marine ecology and aquaculture to underwater construction and archaeology.<n>Slurpp is over 200X faster than existing diffusion-based methods while offering 3 dB improvement in PSNR on synthetic benchmarks.
  arXiv  Detail & Related papers  (2025-07-10T16:02:07Z)
• Fast Underwater Scene Reconstruction using Multi-View Stereo and Physical Imaging [5.676974245780037]
  We propose a novel method that integrates Multi-View Stereo absorption (MVS) with a physics-based underwater image formation model.<n>By leveraging the medium to estimate the medium parameters and combining this with a color for rendering, we restore the true colors of underwater scenes.<n> Experimental results show that our method enables high-quality synthesis of novel views in scattering media, clear views restoration by removing the medium, and outperforms existing methods in rendering quality and training efficiency.
  arXiv  Detail & Related papers  (2025-01-21T04:35:27Z)
• Learning Heavily-Degraded Prior for Underwater Object Detection [59.5084433933765]
  This paper seeks transferable prior knowledge from detector-friendly images. It is based on statistical observations that, the heavily degraded regions of detector-friendly (DFUI) and underwater images have evident feature distribution gaps. Our method with higher speeds and less parameters still performs better than transformer-based detectors.
  arXiv  Detail & Related papers  (2023-08-24T12:32:46Z)
• SUCRe: Leveraging Scene Structure for Underwater Color Restoration [1.9490160607392462]
  We introduce SUCRe, a novel method that exploits the scene's 3D structure for underwater color restoration. We conduct extensive quantitative and qualitative analyses of our approach in a variety of scenarios ranging from natural light to deep-sea environments.
  arXiv  Detail & Related papers  (2022-12-18T16:53:13Z)
• Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion [54.151979979158085]
  We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
  arXiv  Detail & Related papers  (2022-11-21T17:42:42Z)
• Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation [111.89519571205778]
  In this work, we propose an alternative domain-adaptive approach to depth estimation. Our novel two-step structure first trains a depth estimation network with labeled synthetic images in a supervised manner. The results of our experiments show that the proposed method improves the network's performance on real images by a considerable margin.
  arXiv  Detail & Related papers  (2021-09-24T08:11:34Z)
• Generalize Ultrasound Image Segmentation via Instant and Plug & Play Style Transfer [65.71330448991166]
  Deep segmentation models generalize to images with unknown appearance. Retraining models leads to high latency and complex pipelines. We propose a novel method for robust segmentation under unknown appearance shifts.
  arXiv  Detail & Related papers  (2021-01-11T05:45:30Z)
• Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [59.906948203578544]
  We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object. We first estimate per-view depth maps using a deep multi-view stereo network. These depth maps are used to coarsely align the different views. We propose a novel multi-view reflectance estimation network architecture.
  arXiv  Detail & Related papers  (2020-03-27T21:28:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.