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

• URL: http://arxiv.org/abs/2410.08092v1
• Date: Thu, 10 Oct 2024 16:33:56 GMT
• Title: UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images
• Authors: Zeyu Chen, Jingyi Tang, Gu Wang, Shengquan Li, Xinghui Li, Xiangyang Ji, Xiu Li,
• Abstract summary: We propose 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.
• Score: 63.32490897641344
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• UMono: Physical Model Informed Hybrid CNN-Transformer Framework for Underwater Monocular Depth Estimation [5.596432047035205]
  Underwater monocular depth estimation serves as the foundation for tasks such as 3D reconstruction of underwater scenes. Existing methods fail to consider the unique characteristics of underwater environments. In this paper, an end-to-end learning framework for underwater monocular depth estimation called UMono is presented.
  arXiv  Detail & Related papers  (2024-07-25T07:52:11Z)
• A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation [19.204227769408725]
  Existing underwater image enhancement approaches fail to accurately estimate imaging model parameters such as depth and veiling light. We propose a model-guided framework for jointly training a Deep Degradation Model with any advanced UIE model. Our framework achieves remarkable enhancement results across diverse underwater scenes.
  arXiv  Detail & Related papers  (2024-07-05T03:10:13Z)
• Scene 3-D Reconstruction System in Scattering Medium [9.044356059297595]
  Existing underwater 3D reconstruction systems still face challenges such as extensive training time and low efficiency. This paper proposes an improved underwater 3D reconstruction system to address these issues and achieve rapid, high-quality 3D reconstruction.
  arXiv  Detail & Related papers  (2023-12-14T14:55:16Z)
• 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)
• MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction [72.05649682685197]
  State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views. This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints. Motivated by recent advances in the area of monocular geometry prediction, we explore the utility these cues provide for improving neural implicit surface reconstruction.
  arXiv  Detail & Related papers  (2022-06-01T17:58:15Z)
• Neural 3D Reconstruction in the Wild [86.6264706256377]
  We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections. We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.
  arXiv  Detail & Related papers  (2022-05-25T17:59:53Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• 3D Surface Reconstruction From Multi-Date Satellite Images [11.84274417463238]
  We propose an extension of Structure from Motion (SfM) based pipeline that allows us to reconstruct point clouds from multiple satellite images. We provide a detailed description of several steps that are mandatory to exploit state-of-the-art mesh reconstruction algorithms in the context of satellite imagery. We show that the proposed pipeline combined with current meshing algorithms outperforms state-of-the-art point cloud reconstruction algorithms in terms of completeness and median error.
  arXiv  Detail & Related papers  (2021-02-04T09:23:21Z)
• 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.