3 Hits in 1.9 sec

PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction [article]

Yifei Shi, Kai Xu, Matthias Niessner, Szymon Rusinkiewicz, Thomas Funkhouser
2018 arXiv   pre-print
We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction.  ...  from other images.We train the network on 10 million triplets of coplanar and non-coplanar patches, and evaluate on a new coplanarity benchmark created from commodity RGB-D scans.  ...  Acknowledgement We are grateful to Min Liu, Zhan Shi, Lintao Zheng, and Maciej Halber for their help on data preprocessing. We also thank Yizhong Zhang for the early discussions.  ... 
arXiv:1803.08407v3 fatcat:yuv2u7aihjbafpdo3vupu3gk4u

High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review

Jianwei Li, Wei Gao, Yihong Wu, Yangdong Liu, Yanfei Shen
2022 Computational Visual Media  
The advent of consumer RGB-D cameras has made a profound advance in indoor scene reconstruction.  ...  We here review high-quality 3D indoor scene reconstruction methods using consumer RGB-D cameras.  ...  PlaneMatch [109] densely models the environment with plane information through a CNN that takes in RGB, depth, and normal information of a planar patch in an image, and outputs a descriptor to find coplanar  ... 
doi:10.1007/s41095-021-0250-8 fatcat:z6ywcn4zujbptjaqrwkwhoyquu

Plane Pair Matching for Efficient 3D View Registration [article]

Adrien Kaiser, José Alonso Ybanez Zepeda, Tamy Boubekeur
2020 arXiv   pre-print
We validate our approach on a toy example and present quantitative experiments on a public RGB-D dataset, comparing against recent state-of-the-art methods.  ...  They predict local and global patch coplanarity in different RGB-D views of a scene and aggregate all coplanarity constraints as well as point correspondences into a robust optimization framework that  ...  More recently, Shi et al. presented PlaneMatch [30] , a learning approach to planar feature matching and registration in RGB-D frames.  ... 
arXiv:2001.07058v1 fatcat:ymhj4az3gvazfgkhpjo5ctyx4a