Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization

08/06/2021
by   Antoni Rosinol, et al.
0

Meshes are commonly used as 3D maps since they encode the topology of the scene while being lightweight. Unfortunately, 3D meshes are mathematically difficult to handle directly because of their combinatorial and discrete nature. Therefore, most approaches generate 3D meshes of a scene after fusing depth data using volumetric or other representations. Nevertheless, volumetric fusion remains computationally expensive both in terms of speed and memory. In this paper, we leapfrog these intermediate representations and build a 3D mesh directly from a depth map and the sparse landmarks triangulated with visual odometry. To this end, we formulate a non-smooth convex optimization problem that we solve using a primal-dual method. Our approach generates a smooth and accurate 3D mesh that substantially improves the state-of-the-art on direct mesh reconstruction while running in real-time.

READ FULL TEXT

page 3

page 5

page 7

research
03/11/2018

An Efficient Volumetric Mesh Representation for Real-time Scene Reconstruction using Spatial Hashing

Mesh plays an indispensable role in dense real-time reconstruction essen...
research
03/04/2019

Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities

Visual-Inertial Odometry (VIO) algorithms typically rely on a point clou...
research
11/03/2020

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

3D shape representations that accommodate learning-based 3D reconstructi...
research
01/08/2018

Reversible Harmonic Maps between Discrete Surfaces

Information transfer between triangle meshes is of great importance in c...
research
10/03/2022

Probabilistic Volumetric Fusion for Dense Monocular SLAM

We present a novel method to reconstruct 3D scenes from images by levera...
research
09/19/2023

Using an Uncrewed Surface Vehicle to Create a Volumetric Model of Non-Navigable Rivers and Other Shallow Bodies of Water

Non-navigable rivers and retention ponds play important roles in bufferi...
research
01/06/2021

Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D Learning

This paper addresses outdoor terrain mapping using overhead images obtai...

Please sign up or login with your details

Forgot password? Click here to reset