Le Hui

Prof. Dr. Le Hui

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LHLe Hui
Le Hui
MCMingmei Cheng
Mingmei Cheng
JXJin Xie
Jin Xie
JYJian Yang
Jian Yang
MCMing-Ming Cheng
Ming-Ming Cheng
Point cloud based retrieval for place recognition is still a challenging problem since the drastic appearance changes of scenes due to seasonal or artificial changes in the environments. Existing deep learning based global descriptors for the retrieval task usually consume a large amount of computational resources ( $e.g$ ., memory), which may not be suitable for the cases of limited hardware resources. In this paper, we develop an efficient point cloud learning network (EPC-Net) to generate global descriptors of point clouds for place recognition. While obtaining good performance, it can greatly reduce computational memory and inference time. First, we propose a lightweight but effective neural network module, called ProxyConv, to aggregate the local geometric features of point clouds. We leverage the adjacency matrix and proxy points to simplify the original edge convolution for lower memory consumption. Then, we design a lightweight grouped VLAD network to form global descriptors for retrieval. Compared with the original VLAD network, we propose a grouped fully connected layer to decompose the high-dimensional vectors into a group of low-dimensional vectors, which can reduce the number of parameters of the network and maintain the discrimination of the feature vector. Finally, we further develop a simple version of EPC-Net, called EPC-Net-L, which consists of two ProxyConv modules and one max pooling layer to aggregate global descriptors. By distilling the knowledge from EPC-Net, EPC-Net-L can obtain discriminative global descriptors for retrieval. Extensive experiments on the Oxford dataset and three in-house datasets demonstrate that our method achieves good results with lower parameters, FLOPs, GPU memory, and shorter inference time. Our code is available at https://github.com/fpthink/EPC-Net .

11 November 2022
Verified
Book Chapter
Closed access
PDF file
LHLe Hui
Le Hui
LWLingpeng Wang
Lingpeng Wang
LTLinghua Tang
Linghua Tang
KLKaihao Lan
Kaihao Lan
JXJin Xie
Jin Xie
JYJian Yang
Jian Yang

30 October 2022
Verified
Book Chapter
Closed access
PDF file
MHMu He
Mu He
LHLe Hui
Le Hui
YBYikai Bian
Yikai Bian
JRJian Ren
Jian Ren
JXJin Xie
Jin Xie
JYJian Yang
Jian Yang

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YZYun Zhu
Yun Zhu
LHLe Hui
Le Hui
YSYaqi Shen
Yaqi Shen
JXJin Xie
Jin Xie
Current 3D object detection methods for indoor scenes mainly follow the voting-and-grouping strategy to generate proposals. However, most methods utilize instance-agnostic groupings, such as ball query, leading to inconsistent semantic information and inaccurate regression of the proposals. To this end, we propose a novel superpoint grouping network for indoor anchor-free one-stage 3D object detection. Specifically, we first adopt an unsupervised manner to partition raw point clouds into superpoints, areas with semantic consistency and spatial similarity. Then, we design a geometry-aware voting module that adapts to the centerness in anchor-free detection by constraining the spatial relationship between superpoints and object centers. Next, we present a superpoint-based grouping module to explore the consistent representation within proposals. This module includes a superpoint attention layer to learn feature interaction between neighboring superpoints, and a superpoint-voxel fusion layer to propagate the superpoint-level information to the voxel level. Finally, we employ effective multiple matching to capitalize on the dynamic receptive fields of proposals based on superpoints during the training. Experimental results demonstrate our method achieves state-of-the-art performance on ScanNet V2, SUN RGB-D, and S3DIS datasets in the indoor one-stage 3D object detection. Source code is available at https://github.com/zyrant/SPGroup3D.

3 November 2022
Verified
Book Chapter
Closed access
PDF file
YHYuehui Han
Yuehui Han
LHLe Hui
Le Hui
HJHaobo Jiang
Haobo Jiang
JQJianjun Qian
Jianjun Qian
JXJin Xie
Jin Xie