paper-with-me

홈 › Papers

PlueckerNet: Learn to Register 3D Line Reconstructions

2020-12-02 · Liu Liu, Hongdong Li, Haodong Yao, Ruyi Zha

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.

📄 PDF Abstract BibTeX arXiv:2012.01096

Code (2)

Liumouliu/PlueckerNet 공식 구현 pytorch
Mind23-2/MindCode-164

Tasks

Translation

Similar Papers 제목 키워드 기반

ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration

2025-03-21 · CVPR 2025 1 · Johan Edstedt, André Mateus, Alberto Jaenal

Structure-from-Motion (SfM) is the task of estimating 3D structure and camera poses from images. We define Collaborative SfM (ColabSfM) as sharing distributed SfM reconstructions. Sharing maps requires estimating a joint…

Dataset GenerationPoint Cloud Registration

PluckerNet: Learn To Register 3D Line Reconstructions

2021-06-19 · CVPR 2021 1 · Liu Liu, Hongdong Li, Haodong Yao, Ruyi Zha

Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve line correspondences and relative pose between reconstructions. This paper proposes a ne…

Translation

Zero NeRF: Registration with Zero Overlap

2022-11-22 · Casey Peat, Oliver Batchelor, Richard Green, James Atlas

We present Zero-NeRF, a projective surface registration method that, to the best of our knowledge, offers the first general solution capable of alignment between scene representations with minimal or zero visual correspo…

NeRF

LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors

2020-08-01 · ECCV 2020 8 · Jan Brejcha, Michal Lukáč, Yannick Hold-Geoffroy, Oliver Wang 외

We introduce a solution to large scale Augmented Reality for outdoor scenes by registering camera images to textured Digital Elevation Models (DEMs). To accomodate the inherent differences in appearance between real imag…

Patch Matching

PhotoReg: Photometrically Registering 3D Gaussian Splatting Models

2024-10-07 · Ziwen Yuan, Tianyi Zhang, Matthew Johnson-Roberson, Weiming Zhi

Building accurate representations of the environment is critical for intelligent robots to make decisions during deployment. Advances in photorealistic environment models have enabled robots to develop hyper-realistic re…

3DGS