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.
no code implementations • 4 Jan 2023 • Minghan Zhu, Lingting Ge, Panqu Wang, Huei Peng
We propose a novel approach for monocular 3D object detection by leveraging local perspective effects of each object.
1 code implementation • 10 Jul 2022 • Lei Yang, Xinyu Zhang, Li Wang, Minghan Zhu, Chuang Zhang, Jun Li
Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4. 65% improvement on AP@0. 7 for car detection, reaching 18. 54% AP@0. 7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard.
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.
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.
no code implementations • 7 Jul 2021 • Yuanxin Zhong, Minghan Zhu, Huei Peng
A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper.
1 code implementation • 1 May 2021 • Lei Yang, Xinyu Zhang, Li Wang, Minghan Zhu, Jun Li
3D object detection with a single image is an essential and challenging task for autonomous driving.
1 code implementation • 29 Mar 2021 • Minghan Zhu, Songan Zhang, Yuanxin Zhong, Pingping Lu, Huei Peng, John Lenneman
This paper proposes a method to extract the position and pose of vehicles in the 3D world from a single traffic camera.
1 code implementation • 4 Nov 2020 • Yuanxin Zhong, Minghan Zhu, Huei Peng
Object detection and tracking is a key task in autonomy.
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.
no code implementations • 12 Dec 2019 • Yiqun Dong, Yuanxin Zhong, Wenbo Yu, Minghan Zhu, Pingping Lu, Yeyang Fang, Jiajun Hong, Huei Peng
The main goal of this paper is to introduce the data collection effort at Mcity targeting automated vehicle development.