1 code implementation • 25 May 2024 • Xue Zhang, Si-Yuan Cao, Fang Wang, Runmin Zhang, Zhe Wu, Xiaohan Zhang, Xiaokai Bai, Hui-Liang Shen
In this paper, we address this issue by improving the performance of efficient single-branch structures.
no code implementations • 30 Mar 2024 • Runmin Zhang, Zhu Yu, Zehua Sheng, Jiacheng Ying, Si-Yuan Cao, Shu-Jie Chen, Bailin Yang, Junwei Li, Hui-Liang Shen
Our transformer block contains a noise-robust cross-attention (NRCA) module and a spatially variant feature fusion (SVFF) module.
1 code implementation • 26 May 2023 • Xue Zhang, Xiao-Han Zhang, Jiacheng Ying, Zehua Sheng, Heng Yu, Chunguang Li, Hui-Liang Shen
In this paper, we propose a novel target-aware fusion strategy for multispectral pedestrian detection, named TFDet.
no code implementations • 2 Mar 2023 • Shuhang Zheng, Yixuan Li, Zhu Yu, Beinan Yu, Si-Yuan Cao, Minhang Wang, Jintao Xu, Rui Ai, Weihao Gu, Lun Luo, Hui-Liang Shen
The experimental results evaluated on the KITTI dataset show that, with only a small set of training data, I2P-Rec achieves recall rates at Top-1\% over 80\% and 90\%, when localizing monocular and stereo images on point cloud maps, respectively.
no code implementations • ICCV 2023 • Zhu Yu, Zehua Sheng, Zili Zhou, Lun Luo, Si-Yuan Cao, Hong Gu, Huaqi Zhang, Hui-Liang Shen
We extract 2D feature map from images and transform the sparse depth map to point cloud to extract sparse 3D features.
1 code implementation • CVPR 2023 • Zehua Sheng, Zhu Yu, Xiongwei Liu, Si-Yuan Cao, Yuqi Liu, Hui-Liang Shen, Huaqi Zhang
Instead of aligning the input images via conventional stereo matching, we aggregate structures from the guidance image to estimate a clean structure map for the noisy target image, which is then used to regress the final denoising result with a spatially variant linear representation model.
1 code implementation • CVPR 2023 • Si-Yuan Cao, Runmin Zhang, Lun Luo, Beinan Yu, Zehua Sheng, Junwei Li, Hui-Liang Shen
We propose the Recurrent homography estimation framework using Homography-guided image Warping and Focus transformer (FocusFormer), named RHWF.
1 code implementation • CVPR 2022 • Si-Yuan Cao, Jianxin Hu, Zehua Sheng, Hui-Liang Shen
On a variety of datasets, the 2-scale IHN outperforms all competitors by a large gap.
2 code implementations • 14 Oct 2021 • Xue Zhang, Zehua Sheng, Hui-Liang Shen
We also introduce a novel focus-picking loss function to improve classification accuracy by encouraging FocusNet to focus on the most confusing classes.
1 code implementation • 1 Sep 2021 • Lun Luo, Si-Yuan Cao, Bin Han, Hui-Liang Shen, Junwei Li
Recognizing places using Lidar in large-scale environments is challenging due to the sparse nature of point cloud data.
no code implementations • 17 Aug 2021 • Ze-Hua Sheng, Hui-Liang Shen, Bo-Wen Yao, Huaqi Zhang
Experimental results show that, our algorithm can efficiently restore color images with higher SNR and richer details from the mono-color image pairs, and achieves good performance in solving the color bleeding problem.
no code implementations • 9 Jun 2021 • Si-Yuan Cao, Beinan Yu, Lun Luo, Shu-Jie Chen, Chunguang Li, Hui-Liang Shen
PCNet is constructed under the inspiration of the well-known phase congruency.
no code implementations • 15 Feb 2017 • Shu-Jie Chen, Hui-Liang Shen
In this paper, a new measure, namely normalized total gradient (NTG), is proposed for multispectral image registration.