SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification

• URL: http://arxiv.org/abs/2502.02657v1
• Date: Tue, 04 Feb 2025 19:00:49 GMT
• Title: SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification
• Authors: Yifu Tao, Maurice Fallon,
• Abstract summary: We present a neural radiance field (NeRF) based large-scale reconstruction system that fuses lidar and vision data. Our system adopts the state-of-the-art NeRF representation to additionally incorporate lidar. We demonstrate the reconstruction system using a multi-camera, lidar sensor suite in experiments involving both robot-mounted and handheld scanning.
• Score: 0.0
• License:
• Abstract: We present a neural radiance field (NeRF) based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photorealistic texture. Our system adopts the state-of-the-art NeRF representation to additionally incorporate lidar. Adding lidar data adds strong geometric constraints on the depth and surface normals, which is particularly useful when modelling uniform texture surfaces which contain ambiguous visual reconstruction cues. Furthermore, we estimate the epistemic uncertainty of the reconstruction as the spatial variance of each point location in the radiance field given the sensor observations from camera and lidar. This enables the identification of areas that are reliably reconstructed by each sensor modality, allowing the map to be filtered according to the estimated uncertainty. Our system can also exploit the trajectory produced by a real-time pose-graph lidar SLAM system during online mapping to bootstrap a (post-processed) Structure-from-Motion (SfM) reconstruction procedure reducing SfM training time by up to 70%. It also helps to properly constrain the overall metric scale which is essential for the lidar depth loss. The globally-consistent trajectory can then be divided into submaps using Spectral Clustering to group sets of co-visible images together. This submapping approach is more suitable for visual reconstruction than distance-based partitioning. Each submap is filtered according to point-wise uncertainty estimates and merged to obtain the final large-scale 3D reconstruction. We demonstrate the reconstruction system using a multi-camera, lidar sensor suite in experiments involving both robot-mounted and handheld scanning. Our test datasets cover a total area of more than 20,000 square metres, including multiple university buildings and an aerial survey of a multi-storey.

Related papers

• PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map [30.06864329412246]
  We propose a novel map representation that unifies a continuous signed distance field and a Gaussian splatting radiance field within an elastic and compact point-based implicit neural map. We devise a LiDAR-visual SLAM system called PINGS using the proposed map representation and evaluate it on several challenging large-scale datasets.
  arXiv  Detail & Related papers  (2025-02-09T03:06:19Z)
• CoCPF: Coordinate-based Continuous Projection Field for Ill-Posed Inverse Problem in Imaging [78.734927709231]
  Sparse-view computed tomography (SVCT) reconstruction aims to acquire CT images based on sparsely-sampled measurements. Due to ill-posedness, implicit neural representation (INR) techniques may leave considerable holes'' (i.e., unmodeled spaces) in their fields, leading to sub-optimal results. We propose the Coordinate-based Continuous Projection Field (CoCPF), which aims to build hole-free representation fields for SVCT reconstruction.
  arXiv  Detail & Related papers  (2024-06-21T08:38:30Z)
• SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection [4.6102302191645075]
  We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions. We exploit the trajectory from a real-time lidar SLAM system to bootstrap a Structure-from-Motion (SfM) procedure. We use submapping to scale the system to large-scale environments captured over long trajectories.
  arXiv  Detail & Related papers  (2024-03-11T16:31:25Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids [84.90863397388776]
  We propose to directly use signed distance function (SDF) in sparse voxel block grids for fast and accurate scene reconstruction without distances. Our globally sparse and locally dense data structure exploits surfaces' spatial sparsity, enables cache-friendly queries, and allows direct extensions to multi-modal data. Experiments show that our approach is 10x faster in training and 100x faster in rendering while achieving comparable accuracy to state-of-the-art neural implicit methods.
  arXiv  Detail & Related papers  (2023-05-22T16:50:19Z)
• BS3D: Building-scale 3D Reconstruction from RGB-D Images [25.604775584883413]
  We propose an easy-to-use framework for acquiring building-scale 3D reconstruction using a consumer depth camera. Unlike complex and expensive acquisition setups, our system enables crowd-sourcing, which can greatly benefit data-hungry algorithms.
  arXiv  Detail & Related papers  (2023-01-03T11:46:14Z)
• Semi-signed neural fitting for surface reconstruction from unoriented point clouds [53.379712818791894]
  We propose SSN-Fitting to reconstruct a better signed distance field. SSN-Fitting consists of a semi-signed supervision and a loss-based region sampling strategy. We conduct experiments to demonstrate that SSN-Fitting achieves state-of-the-art performance under different settings.
  arXiv  Detail & Related papers  (2022-06-14T09:40:17Z)
• TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning [20.81202315793742]
  This paper develops a joint 2D-3D learning approach to reconstruct a local metric-semantic mesh at each camera maintained by a visual odometry algorithm. The mesh can be assembled into a global environment model to capture the terrain topology and semantics during online operation.
  arXiv  Detail & Related papers  (2022-04-23T05:18:39Z)
• 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)
• OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems [88.41004332322788]
  We present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation. We integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency.
  arXiv  Detail & Related papers  (2020-03-18T05:52:10Z)

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.