1 code implementation • 25 Dec 2023 • Jingwei Song, Ray Zhang, Qiuchen Zhu, Jianyu Lin, Maani Ghaffari
Conclusion: The proposed BDIS-SLAM is a lightweight stereo dense SLAM system for MIS.
no code implementations • 24 Oct 2023 • Joey Wilson, Yuewei Fu, Joshua Friesen, Parker Ewen, Andrew Capodieci, Paramsothy Jayakumar, Kira Barton, Maani Ghaffari
In this paper, we develop a modular neural network for real-time semantic mapping in uncertain environments, which explicitly updates per-voxel probabilistic distributions within a neural network layer.
1 code implementation • 6 Oct 2023 • Tzu-Yuan Lin, Minghan Zhu, Maani Ghaffari
This paper proposes an equivariant neural network that takes data in any semi-simple Lie algebra as input.
no code implementations • ICCV 2023 • Minghan Zhu, Shizhong Han, Hong Cai, Shubhankar Borse, Maani Ghaffari, Fatih Porikli
In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation.
2 code implementations • 21 Sep 2022 • Joey Wilson, Yuewei Fu, Arthur Zhang, Jingyu Song, Andrew Capodieci, Paramsothy Jayakumar, Kira Barton, Maani Ghaffari
Robotic perception is currently at a cross-roads between modern methods, which operate in an efficient latent space, and classical methods, which are mathematically founded and provide interpretable, trustworthy results.
1 code implementation • 16 Sep 2022 • Yifan Xu, Theodor Chakhachiro, Tribhi Kathuria, Maani Ghaffari
This work proposes a new framework for a socially-aware dynamic local planner in crowded environments by building on the recently proposed Trajectory-ranked Maximum Entropy Deep Inverse Reinforcement Learning (T-MEDIRL).
1 code implementation • CVPR 2023 • Minghan Zhu, Maani Ghaffari, William A. Clark, Huei Peng
We also propose a permutation layer to recover SO(3) features from spherical features to preserve the capacity to distinguish rotations.
2 code implementations • 6 May 2022 • Jingwei Song, Qiuchen Zhu, Jianyu Lin, Maani Ghaffari
The patch-based fast disparity searching algorithm is adopted for the rectified stereo images.
1 code implementation • 14 Mar 2022 • Joey Wilson, Jingyu Song, Yuewei Fu, Arthur Zhang, Andrew Capodieci, Paramsothy Jayakumar, Kira Barton, Maani Ghaffari
This work addresses a gap in semantic scene completion (SSC) data by creating a novel outdoor data set with accurate and complete dynamic scenes.
no code implementations • 5 Jan 2022 • Jingwei Song, Mitesh Patel, Maani Ghaffari
This paper proposes a new image-based localization framework that explicitly localizes the camera/robot by fusing Convolutional Neural Network (CNN) and sequential images' geometric constraints.
2 code implementations • 6 Aug 2021 • Aishwarya Unnikrishnan, Joey Wilson, Lu Gan, Andrew Capodieci, Paramsothy Jayakumar, Kira Barton, Maani Ghaffari
This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model.
1 code implementation • 21 Jul 2021 • Minghan Zhu, Maani Ghaffari, Huei Peng
We learn an embedding for each point cloud in a feature space that preserves the SO(3)-equivariance property, enabled by recent developments in equivariant neural networks.
1 code implementation • 14 Jun 2021 • Jingwei Song, Qiuchen Zhu, Jianyu Lin, Maani Ghaffari
Our Bayesian method correctly balances the probability of the patch for stereo images at different scales.
5 code implementations • 6 Dec 2020 • Jiunn-Kai Huang, Chenxi Feng, Madhav Achar, Maani Ghaffari, Jessy W. Grizzle
By modeling the calibration parameters as an element of a special matrix Lie Group, we achieve a unifying view of calibration for different types of LiDARs.
1 code implementation • 10 Nov 2020 • Ray Zhang, Tzu-Yuan Lin, Chien Erh Lin, Steven A. Parkison, William Clark, Jessy W. Grizzle, Ryan M. Eustice, Maani Ghaffari
This paper reports on a novel nonparametric rigid point cloud registration framework that jointly integrates geometric and semantic measurements such as color or semantic labels into the alignment process and does not require explicit data association.
1 code implementation • 10 May 2020 • Jingwei Song, Mitesh Patel, Ashkan Jasour, Maani Ghaffari
In this paper, we present a statistical inference on the element-wise uncertainty quantification of the estimated deforming 3D shape points in the case of the exact low-rank SDP problem.
2 code implementations • 21 Mar 2020 • Minghan Zhu, Maani Ghaffari, Yuanxin Zhong, Pingping Lu, Zhong Cao, Ryan M. Eustice, Huei Peng
In contrast to the current point-to-point loss evaluation approach, the proposed 3D loss treats point clouds as continuous objects; therefore, it compensates for the lack of dense ground truth depth due to LIDAR's sparsity measurements.
1 code implementation • 2 Feb 2020 • Sahib Singh Dhanjal, Maani Ghaffari, Ryan M. Eustice
The proposed algorithm can globally localize and track a smartphone (or robot) with a priori unknown location, and with a semi-accurate prior map (error within 0. 8 m) of the WiFi Access Points (AP).
Robotics Signal Processing
2 code implementations • 8 Jan 2020 • William Clark, Maani Ghaffari, Anthony Bloch
The functions can be defined on arbitrary smooth manifolds where the action of a Lie group aligns them.
1 code implementation • 2 Dec 2019 • Xi Lin, Dingyi Sun, Tzu-Yuan Lin, Ryan M. Eustice, Maani Ghaffari
The experimental evaluations using publicly available RGB-D benchmarks show that the developed keyframe selection technique using continuous visual odometry outperforms its robust dense (and direct) visual odometry equivalent.
1 code implementation • 1 Oct 2019 • Tzu-Yuan Lin, William Clark, Ryan M. Eustice, Jessy W. Grizzle, Anthony Bloch, Maani Ghaffari
In this paper, we extend the recently developed continuous visual odometry framework for RGB-D cameras to an adaptive framework via online hyperparameter learning.
2 code implementations • 10 Sep 2019 • Lu Gan, Ray Zhang, Jessy W. Grizzle, Ryan M. Eustice, Maani Ghaffari
This paper develops a Bayesian continuous 3D semantic occupancy map from noisy point cloud measurements.
Robotics
4 code implementations • 23 Aug 2019 • Jiunn-Kai Huang, Shoutian Wang, Maani Ghaffari, Jessy W. Grizzle
Because of the LiDAR sensors' nature, rapidly changing ambient lighting will not affect the detection of a LiDARTag; hence, the proposed fiducial marker can operate in a completely dark environment.
1 code implementation • 19 Apr 2019 • Ross Hartley, Maani Ghaffari, Ryan M. Eustice, Jessy W. Grizzle
This filter combines contact-inertial dynamics with forward kinematic corrections to estimate pose and velocity along with all current contact points.
Robotics
1 code implementation • 3 Apr 2019 • Maani Ghaffari, William Clark, Anthony Bloch, Ryan M. Eustice, Jessy W. Grizzle
This paper reports on a novel formulation and evaluation of visual odometry from RGB-D images.