PlueckerNet: Learn to Register 3D Line Reconstructions
This work provides a more robust and precise method for 3D line reconstruction registration, which is beneficial for applications in computer vision and robotics that rely on accurate 3D scene understanding.
This paper addresses the problem of aligning two partially-overlapped 3D line reconstructions by simultaneously solving for correspondences and relative pose. The proposed neural network-based method significantly outperforms baselines in registration precision (rotation and translation) on both indoor and outdoor datasets.
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.