1 code implementation • 14 Apr 2024 • Fei Xue, Ignas Budvytis, Daniel Olmeda Reino, Roberto Cipolla
However, in spite of high efficiency, APRs and SCRs have limited accuracy especially in large-scale outdoor scenes; HMs are accurate but need to store a large number of 2D descriptors for matching, resulting in poor efficiency.
no code implementations • 11 Apr 2024 • Fei Xue, Ignas Budvytis, Roberto Cipolla
Humans localize themselves efficiently in known environments by first recognizing landmarks defined on certain objects and their spatial relationships, and then verifying the location by aligning detailed structures of recognized objects with those in the memory.
no code implementations • 21 Nov 2023 • Jiuchen Zhang, Fei Xue, Qi Xu, Jung-Ah Lee, Annie Qu
In this paper, we propose an individualized dynamic latent factor model for irregular multi-resolution time series data to interpolate unsampled measurements of time series with low resolution.
1 code implementation • CVPR 2023 • Fei Xue, Ignas Budvytis, Roberto Cipolla
Visual localization is a fundamental task for various applications including autonomous driving and robotics.
1 code implementation • CVPR 2023 • Fei Xue, Ignas Budvytis, Roberto Cipolla
Previous methods solve feature matching and pose estimation using a two-stage process by first finding matches and then estimating the pose.
no code implementations • CVPR 2022 • Fei Xue, Ignas Budvytis, Daniel Olmeda Reino, Roberto Cipolla
Hierarchical frameworks consisting of both coarse and fine localization are often used as the standard pipeline for large-scale visual localization.
1 code implementation • 7 Jun 2021 • Fei Xue, Rong Ma, Hongzhe Li
Blockwise missing data occurs frequently when we integrate multisource or multimodality data where different sources or modalities contain complementary information.
1 code implementation • 8 May 2021 • Dong Liang, Fei Xue, Ling Li
Concealed object detection in Terahertz imaging is an urgent need for public security and counter-terrorism.
no code implementations • 9 Mar 2021 • D. J. P. de Sousa, Fei Xue, J. P. Wang, P. M. Haney, Tony Low
We study the current-induced torques in asymmetric magnetic tunnel junctions containing a conventional ferromagnet and a magnetic Weyl semimetal contact.
Mesoscale and Nanoscale Physics
no code implementations • 21 Sep 2020 • Qiuyuan Wang, Zike Yan, Junqiu Wang, Fei Xue, Wei Ma, Hongbin Zha
To address these problems, we leverage a line flow to encode the coherence of line segment observations of the same 3D line along the temporal dimension, which has been neglected in prior SLAM systems.
no code implementations • CVPR 2020 • Fei Xue, Xin Wu, Shaojun Cai, Junqiu Wang
We propose to construct a view graph to excavate the information of the whole given sequence for absolute camera pose estimation.
Ranked #3 on Camera Localization on Oxford RobotCar Full
no code implementations • CVPR 2020 • Shunkai Li, Xin Wang, Yingdian Cao, Fei Xue, Zike Yan, Hongbin Zha
In this paper, we propose an online meta-learning algorithm to enable VO networks to continuously adapt to new environments in a self-supervised manner.
no code implementations • 14 Jan 2020 • Fei Xue, Yanqing Zhang, Wenzhuo Zhou, Haoda Fu, Annie Qu
An optimal dynamic treatment regime (DTR) consists of a sequence of decision rules in maximizing long-term benefits, which is applicable for chronic diseases such as HIV infection or cancer.
no code implementations • ICCV 2019 • Shunkai Li, Fei Xue, Xin Wang, Zike Yan, Hongbin Zha
As single-view depth estimation is an ill-posed problem, and photometric loss is incapable of discriminating distortion artifacts of warped images, the estimated depth is vague and pose is inaccurate.
no code implementations • ICCV 2019 • Fei Xue, Xin Wang, Zike Yan, Qiuyuan Wang, Junqiu Wang, Hongbin Zha
We propose to leverage the local information in image sequences to support global camera relocalization.
no code implementations • CVPR 2019 • Fei Xue, Xin Wang, Shunkai Li, Qiuyuan Wang, Junqiu Wang, Hongbin Zha
Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem.
no code implementations • 25 Nov 2018 • Fei Xue, Qiuyuan Wang, Xin Wang, Wei Dong, Junqiu Wang, Hongbin Zha
We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks.