# UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images

arXiv: https://arxiv.org/abs/2410.08092 · HTML: https://mlsanity.com/paper/2410.08092/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://mlsanity.com/paper/2312.02145/) (2023)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping](https://mlsanity.com/paper/2305.11003/) (2023)
- [SeaThru-NeRF: Neural Radiance Fields in Scattering Media](https://mlsanity.com/paper/2304.07743/) (2023)
- [SeMask: Semantically Masked Transformers for Semantic Segmentation](https://mlsanity.com/paper/2112.12782/) (2021)
- [Uncertainty Inspired Underwater Image Enhancement](https://mlsanity.com/paper/2207.09689/) (2022)
- [A Generalized Framework for Video Instance Segmentation](https://mlsanity.com/paper/2211.08834/) (2022)
- [RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials](https://mlsanity.com/paper/1901.01535/) (2019)
- [Underwater Light Field Retention : Neural Rendering for Underwater Imaging](https://mlsanity.com/paper/2203.11006/) (2022)
- [SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots](https://mlsanity.com/paper/2011.06252/) (2020)
- [Mask-Free Video Instance Segmentation](https://mlsanity.com/paper/2303.15904/) (2023)
- [Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery](https://mlsanity.com/paper/2304.03384/) (2023)
- [Fusing Concurrent Orthogonal Wide-aperture Sonar Images for Dense Underwater 3D Reconstruction](https://mlsanity.com/paper/2007.10407/) (2020)
- [Light Field-Based Underwater 3D Reconstruction Via Angular Resampling](https://mlsanity.com/paper/2109.02116/) (2021)

## Built on by (most cited first, 1 of 1)

- [MuS-Polar3D: A Benchmark Dataset for Computational Polarimetric 3D Imaging under Multi-Scattering Conditions](https://mlsanity.com/paper/2512.21513/) (2025)

## Abstract (arXiv)

Due to the unique characteristics of underwater environments, accurate 3D reconstruction of underwater objects poses a challenging problem in tasks such as underwater exploration and mapping. Traditional methods that rely on multiple sensor data for 3D reconstruction are time-consuming and face challenges in data acquisition in underwater scenarios. We propose UW-SDF, a framework for reconstructing target objects from multi-view underwater images based on neural SDF. We introduce hybrid geometric priors to optimize the reconstruction process, markedly enhancing the quality and efficiency of neural SDF reconstruction. Additionally, to address the challenge of segmentation consistency in multi-view images, we propose a novel few-shot multi-view target segmentation strategy using the general-purpose segmentation model (SAM), enabling rapid automatic segmentation of unseen objects. Through extensive qualitative and quantitative experiments on diverse datasets, we demonstrate that our proposed method outperforms the traditional underwater 3D reconstruction method and other neural rendering approaches in the field of underwater 3D reconstruction.