PlueckerNet: Learn to Register 3D Line Reconstructions
arXiv:2012.01096
Abstract
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.
arXiv comment12 pages
References in corpus (7)
- Gaussian Error Linear Units (GELUs)
- Linformer: Self-Attention with Linear Complexity
- Growing multiplex networks
- Rethinking Attention with Performers
- Fast 3D Line Segment Detection From Unorganized Point Cloud
- Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem
- Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration