3D Surface Reconstruction from Voxel-based Lidar Data

  title={3D Surface Reconstruction from Voxel-based Lidar Data},
  author={Luis Rold{\~a}o and Raoul de Charette and Anne Verroust-Blondet},
  journal={2019 IEEE Intelligent Transportation Systems Conference (ITSC)},
To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding. In this paper, a 3D surface reconstruction algorithm from heterogeneous density 3D data is presented. The proposed method is based on a TSDF voxel-based representation, where an adaptive neighborhood kernel sourced on a Gaussian confidence evaluation is introduced. This enables to keep a good trade-off between the density of the reconstructed mesh and its accuracy. Experimental… 

Figures and Tables from this paper

Poisson Surface Reconstruction for LiDAR Odometry and Mapping

This paper presents a novel approach for LiDAR odometry and mapping, focusing on improving the mapping quality and at the same time estimating the pose of the vehicle, and represents the map as a triangle mesh computed via Poisson surface reconstruction.

Real-time Registration and Reconstruction with Cylindrical LiDAR Images

This work revisits the LiDAR scan formation and presents a cylindrical range image representation for data from raw scans, equipped with an efficient calibrated spherical projective model.

Revisiting LiDAR Registration and Reconstruction: A Range Image Perspective

Spinning LiDAR data are prevalent for 3D vision tasks. Since LiDAR data is presented in the form of point clouds, expensive 3D operations are usually required. This paper revisits spinning LiDAR scan

Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function

A novel 3D reconstruction, texturing and semantic mapping system using LiDAR and camera sensors using an Adaptive Truncated Signed Distance Function and a Markov Random Field-based data fusion approach to estimate the optimal semantic class for each triangle mesh.

SLAMesh: Real-time LiDAR Simultaneous Localization and Meshing

This work proposes the first CPU-only real-time LiDAR SLAM system that can simultaneously build a mesh map and perform localization against the mesh map, and a novel and direct meshing strategy with Gaussian process reconstruction realizes the fast building, registration, and updating of mesh maps.

LMSCNet: Lightweight Multiscale 3D Semantic Completion

The ablation studies demonstrate the method is robust to lower density inputs, and that it enables very high speed semantic completion at the coarsest level, and provides a great performance/speed trade-off for mobile-robotics applications.


A generic method to merge meshes produced from Lidar data that allows to tackle the issues of moving objects removal and static scene reconstruction at once is proposed.

Blind Quality of a 3D Reconstructed MESH

This paper proves that metrics based on a reference model (extrinsic metrics) that have been shown to be correlated to subjective interpretation, are able to capture flaws that may occur while reconstructing, and proposes blind mesh quality measures for a reconstructed 3D model.

Guided Depth Completion with Instance Segmentation Fusion in Autonomous Driving Applications

This work proposes to use image instance segmentation to detect objects of interest with pixel-level locations, along with sparse depth data, to support depth completion, and utilizes a two-branch encoder–decoder deep neural network to predict dense accurate depth maps.

Poisson surface reconstruction

A spatially adaptive multiscale algorithm whose time and space complexities are proportional to the size of the reconstructed model, and which reduces to a well conditioned sparse linear system.

A Survey of Surface Reconstruction from Point Clouds

A holistic view of surface reconstruction is considered, which shows a detailed characterization of the field, highlights similarities between diverse reconstruction techniques and provides directions for future work in surface reconstruction.

Marching cubes: A high resolution 3D surface construction algorithm

We present a new algorithm, called marching cubes, that creates triangle models of constant density surfaces from 3D medical data. Using a divide-and-conquer approach to generate inter-slice

Screened poisson surface reconstruction

This work extends Poisson surface reconstruction to explicitly incorporate the points as interpolation constraints and presents several algorithmic improvements that together reduce the time complexity of the solver to linear in the number of points, thereby enabling faster, higher-quality surface reconstructions.

Voxel planes: Rapid visualization and meshification of point cloud ensembles

The voxel planes method is 3 times faster than marching cubes, offers 300 times better compression than Greedy Projection, 10 fold lower error than Marching cubes whilst allowing incremental map updates.

A Statistical Update of Grid Representations from Range Sensors

A statistical model is presented to perform 3D reconstructions of the environment from range sensors using an occupancy grid that takes into account all the available information obtained from the sensor, considering the distances traversed by the rays in each cell and seeking to reduce reconstruction errors caused by discretization.

Automatic Extraction of Manhattan-World Building Masses from 3D Laser Range Scans

We propose a novel approach for the reconstruction of urban structures from 3D point clouds with an assumption of Manhattan World (MW) building geometry; i.e., the predominance of three mutually

A volumetric method for building complex models from range images

This paper presents a volumetric method for integrating range images that is able to integrate a large number of range images yielding seamless, high-detail models of up to 2.6 million triangles.

Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments

A novel, dense approach to laser- based mapping that operates on three-dimensional point clouds obtained from rotating laser sensors that enables real-time capable registration and is able to detect loop closures and to perform map updates in an online fashion is proposed.

OctoMap: an efficient probabilistic 3D mapping framework based on octrees

An open-source framework to generate volumetric 3D environment models based on octrees and uses probabilistic occupancy estimation that represents not only occupied space, but also free and unknown areas and an octree map compression method that keeps the 3D models compact.