no code implementations • 23 Sep 2022 • Mario Srouji, Hugues Thomas, Hubert Tsai, Ali Farhadi, Jian Zhang
Collision avoidance is key for mobile robots and agents to operate safely in the real world.
4 code implementations • 17 Mar 2022 • Meida Chen, Qingyong Hu, Zifan Yu, Hugues Thomas, Andrew Feng, Yu Hou, Kyle McCullough, Fengbo Ren, Lucio Soibelman
Specifically, we introduce a synthetic aerial photogrammetry point clouds generation pipeline that takes full advantage of open geospatial data sources and off-the-shelf commercial packages.
no code implementations • 22 Feb 2021 • David J. Yoon, Haowei Zhang, Mona Gridseth, Hugues Thomas, Timothy D. Barfoot
Though the framework is general to any form of parameter learning and sensor modality, we demonstrate application to feature and uncertainty learning with a deep network for 3D lidar odometry.
Variational Inference Robotics
2 code implementations • 10 Dec 2020 • Hugues Thomas, Ben Agro, Mona Gridseth, Jian Zhang, Timothy D. Barfoot
We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
no code implementations • 7 Dec 2020 • Hugues Thomas
Recent attempts at introducing rotation invariance or equivariance in 3D deep learning approaches have shown promising results, but these methods still struggle to reach the performances of standard 3D neural networks.
9 code implementations • ICCV 2019 • Hugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, Leonidas J. Guibas
Furthermore, these locations are continuous in space and can be learned by the network.
Ranked #1 on 3D Semantic Segmentation on DALES
no code implementations • 1 Aug 2018 • Hugues Thomas, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, Yann Le Gall
This paper introduces a new definition of multiscale neighborhoods in 3D point clouds.
Ranked #12 on Semantic Segmentation on Semantic3D