Acoustic Neural 3D Reconstruction Under Pose Drift

• URL: http://arxiv.org/abs/2503.08930v1
• Date: Tue, 11 Mar 2025 22:18:57 GMT
• Title: Acoustic Neural 3D Reconstruction Under Pose Drift
• Authors: Tianxiang Lin, Mohamad Qadri, Kevin Zhang, Adithya Pediredla, Christopher A. Metzler, Michael Kaess,
• Abstract summary: We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses.<n>Our algorithm does so by parameterizing the 6DoF poses as learnable parameters and backpropagating gradients through the neural and implicit representation.<n>It produces high-fidelity 3D reconstructions even under significant drift.
• Score: 25.123221440440417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses. The accuracy of current state-of-the-art 3D acoustic modeling algorithms is highly dependent on accurate pose estimation; small errors in sensor pose can lead to severe reconstruction artifacts. In this paper, we propose an algorithm that jointly optimizes the neural scene representation and sonar poses. Our algorithm does so by parameterizing the 6DoF poses as learnable parameters and backpropagating gradients through the neural renderer and implicit representation. We validated our algorithm on both real and simulated datasets. It produces high-fidelity 3D reconstructions even under significant pose drift.

Related papers

• HORT: Monocular Hand-held Objects Reconstruction with Transformers [61.36376511119355]
  Reconstructing hand-held objects in 3D from monocular images is a significant challenge in computer vision. We propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects. Our method achieves state-of-the-art accuracy with much faster inference speed, while generalizing well to in-the-wild images.
  arXiv  Detail & Related papers  (2025-03-27T09:45:09Z)
• USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting [45.246178004823534]
  Spike cameras, as an innovative neuromorphic camera that captures scenes with the 0-1 bit stream at 40 kHz, are increasingly employed for the 3D reconstruction task. Previous spike-based 3D reconstruction approaches often employ a casecased pipeline. We propose a synergistic optimization framework, textbfUSP-Gaussian, that unifies spike-based image reconstruction, pose correction, and Gaussian splatting into an end-to-end framework.
  arXiv  Detail & Related papers  (2024-11-15T14:15:16Z)
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• Frequency-based View Selection in Gaussian Splatting Reconstruction [9.603843571051744]
  We investigate the problem of active view selection to perform 3D Gaussian Splatting reconstructions with as few input images as possible. By ranking the potential views in the frequency domain, we are able to effectively estimate the potential information gain of new viewpoints. Our method achieves state-of-the-art results in view selection, demonstrating its potential for efficient image-based 3D reconstruction.
  arXiv  Detail & Related papers  (2024-09-24T21:44:26Z)
• Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis [11.236094544193605]
  Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities. We propose a real-time RGB-D SLAM system that incorporates a novel view synthesis technique, 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-08-10T21:23:08Z)
• NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising [23.876281686625134]
  We present NeSLAM, a framework that achieves accurate and dense depth estimation, robust camera tracking, and realistic synthesis of novel views. Experiments on various indoor datasets demonstrate the effectiveness and accuracy of the system in reconstruction, tracking quality, and novel view synthesis.
  arXiv  Detail & Related papers  (2024-03-29T07:59:37Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)
• NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation [53.25973084799954]
  We present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors. NIKI can learn from both the forward and inverse processes with invertible networks.
  arXiv  Detail & Related papers  (2023-05-15T12:13:24Z)
• Neural Descent for Visual 3D Human Pose and Shape [67.01050349629053]
  We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end. Central to our methodology, is a learning to learn and optimize approach, referred to as HUmanNeural Descent (HUND), which avoids both second-order differentiation.
  arXiv  Detail & Related papers  (2020-08-16T13:38:41Z)

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.