activity
20192023
most citedUncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss

6 citations · 7 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2023★ 1 cited

4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

Minghan Zhu, Shizhong Han, Hong Cai +3

In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation. 4D panoptic segmentation is a benchmark task for autonomous driving that requires recog…

cs.CV2023

MonoEdge: Monocular 3D Object Detection Using Local Perspectives

Minghan Zhu, Lingting Ge, Panqu Wang +1

We propose a novel approach for monocular 3D object detection by leveraging local perspective effects of each object. While the global perspective effect shown as size and position…

cs.CV2022

E2PN: Efficient SE(3)-Equivariant Point Network

Minghan Zhu, Maani Ghaffari, William A. Clark +1

This paper proposes a convolution structure for learning SE(3)-equivariant features from 3D point clouds. It can be viewed as an equivariant version of kernel point convolutions (K…

cs.CV2021

Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations

Minghan Zhu, Maani Ghaffari, Huei Peng

This paper proposes a correspondence-free method for point cloud rotational registration. We learn an embedding for each point cloud in a feature space that preserves the SO(3)-equ…

cs.CV2021

VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars

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. We leverage rich supervision from both detection and segme…

cs.CV2021

Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography

Minghan Zhu, Songan Zhang, Yuanxin Zhong +3

This paper proposes a method to extract the position and pose of vehicles in the 3D world from a single traffic camera. Most previous monocular 3D vehicle detection algorithms focu…