PlueckerNet: Learn to Register 3D Line Reconstructions

12/02/2020
by   Liu Liu, et al.
0

Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions. This paper proposes a neural network based method and it has three modules connected in sequence: (i) a Multilayer Perceptron (MLP) based network takes Pluecker representations of lines as inputs, to extract discriminative line-wise features and matchabilities (how likely each line is going to have a match), (ii) an Optimal Transport (OT) layer takes two-view line-wise features and matchabilities as inputs to estimate a 2D joint probability matrix, with each item describes the matchness of a line pair, and (iii) line pairs with Top-K matching probabilities are fed to a 2-line minimal solver in a RANSAC framework to estimate a six Degree-of-Freedom (6-DoF) rigid transformation. Experiments on both indoor and outdoor datasets show that the registration (rotation and translation) precision of our method outperforms baselines significantly.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/15/2020

Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem

Conventional absolute camera pose via a Perspective-n-Point (PnP) solver...
research
04/10/2020

Robust Line Segments Matching via Graph Convolution Networks

Line matching plays an essential role in structure from motion (SFM) and...
research
03/23/2019

Trifocal Relative Pose from Lines at Points and its Efficient Solution

We present a new minimal problem for relative pose estimation mixing poi...
research
04/23/2023

IDLL: Inverse Depth Line based Visual Localization in Challenging Environments

Precise and real-time localization of unmanned aerial vehicles (UAVs) or...
research
10/08/2021

Pose Refinement with Joint Optimization of Visual Points and Lines

High-precision camera re-localization technology in a pre-established 3D...
research
02/02/2018

Full-pulse Tomographic Reconstruction with Deep Neural Networks

Plasma tomography consists in reconstructing the 2D radiation profile in...
research
07/19/2021

Precise Aerial Image Matching based on Deep Homography Estimation

Aerial image registration or matching is a geometric process of aligning...

Please sign up or login with your details

Forgot password? Click here to reset