1 code implementation • 26 Mar 2024 • Kerui Ren, Lihan Jiang, Tao Lu, Mulin Yu, Linning Xu, Zhangkai Ni, Bo Dai
The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations.
no code implementations • 25 Mar 2024 • Mulin Yu, Tao Lu, Linning Xu, Lihan Jiang, Yuanbo Xiangli, Bo Dai
We show on diverse scenes that our design unlocks the potential for more accurate and detailed surface reconstructions, and at the meantime benefits 3DGS rendering with structures that are more aligned with the underlying geometry.
no code implementations • 16 Jan 2024 • Haibin Zhou, Jun Chang, Tao Lu, Huabing Zhou
Therefore, accurate lane modeling is essential to align prediction results closely with the environment.
no code implementations • 25 Dec 2023 • Hao Wang, Huabing Zhou, Yanduo Zhang, Tao Lu, Jiayi Ma
Scene text spotting is essential in various computer vision applications, enabling extracting and interpreting textual information from images.
1 code implementation • 30 Nov 2023 • Tao Lu, Mulin Yu, Linning Xu, Yuanbo Xiangli, LiMin Wang, Dahua Lin, Bo Dai
Neural rendering methods have significantly advanced photo-realistic 3D scene rendering in various academic and industrial applications.
1 code implementation • 19 Sep 2023 • Jianghao Wu, Guotai Wang, Ran Gu, Tao Lu, Yinan Chen, Wentao Zhu, Tom Vercauteren, Sébastien Ourselin, Shaoting Zhang
The different predictions in these duplicated heads are used to obtain pseudo labels for unlabeled target-domain images and their uncertainty to identify reliable pseudo labels.
1 code implementation • ICCV 2023 • Haisong Liu, Yao Teng, Tao Lu, Haiguang Wang, LiMin Wang
Dense detectors typically follow a two-stage pipeline by first constructing a dense BEV feature and then performing object detection in BEV space, which suffers from complex view transformations and high computation cost.
Ranked #5 on 3D Object Detection on nuScenes Camera Only
no code implementations • 20 Jun 2023 • Jia Fu, Tao Lu, Shaoting Zhang, Guotai Wang
To this end, we propose a novel weakly-supervised method with image-level labels based on semantic features and context information exploration.
1 code implementation • CVPR 2023 • Tao Lu, Xiang Ding, Haisong Liu, Gangshan Wu, LiMin Wang
Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from data scarcity and sparsity.
1 code implementation • 21 Mar 2023 • Haisong Liu, Tao Lu, Yihui Xu, Jia Liu, LiMin Wang
To fuse dense image features and sparse point features, we propose a learnable operator named bidirectional camera-LiDAR fusion module (Bi-CLFM).
Ranked #1 on Scene Flow Estimation on KITTI 2015 Scene Flow Test
no code implementations • 30 Dec 2022 • Yifeng Bie, Shuai You, Xinrui Li, Xuekui Zhang, Tao Lu
Due to the mutual in-dependency among different gas molecules, near one-to-one projection from the principal component to the mixture constituent can be established, leading to a significant simplification of spectral quantification.
1 code implementation • 2 May 2022 • Tao Lu, Chunxu Liu, Youxin Chen, Gangshan Wu, LiMin Wang
In the existing work, each point in the cloud may inevitably be selected as the neighbors of multiple aggregation centers, as all centers will gather neighbor features from the whole point cloud independently.
Ranked #45 on 3D Point Cloud Classification on ScanObjectNN
no code implementations • 31 Mar 2022 • Brosnan Yuen, Yifeng Bie, Duncan Cairns, Geoffrey Harper, Jason Xu, Charles Chang, Xiaodai Dong, Tao Lu
Previous contact tracing systems required the users to perform many manual actions, such as installing smartphone applications, joining wireless networks, or carrying custom user devices.
no code implementations • 19 Feb 2022 • Wei Liu, Cheng Chen, Rui Jiang, Tao Lu, Zixiang Xiong
To address these issues, we develop a novel generative adversarial network, called quad-path cycle consistent adversarial network (QPC-Net), for single image defogging.
no code implementations • 19 Feb 2022 • Wei Liu, Rui Jiang, Cheng Chen, Tao Lu, Zixiang Xiong
The former consists of parallel rain removal path and rain-fog feature extraction path by the rain and derain-fog network and the attention rain-fog feature extraction network (ARFE) , while the latter only contains a synthetic rain transformation path.
no code implementations • 29 Nov 2021 • Minh Tu Hoang, Brosnan Yuen, Kai Ren, Ahmed Elmoogy, Xiaodai Dong, Tao Lu, Robert Westendorp, Kishore Reddy Tarimala
This paper proposes passive WiFi indoor localization.
1 code implementation • CVPR 2022 • Haisong Liu, Tao Lu, Yihui Xu, Jia Liu, Wenjie Li, Lijun Chen
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data.
Ranked #3 on Scene Flow Estimation on Spring
no code implementations • ICLR 2022 • Jiayi Li, Tao Lu, Xiaoge Cao, Yinghao Cai, Shuo Wang
Our approach relies only on human videos and does not require robot demonstration, which facilitates data collection and is more in line with human imitation behavior.
no code implementations • 16 Sep 2021 • Yuanzhi Wang, Tao Lu, Yanduo Zhang, Junjun Jiang, JiaMing Wang, Zhongyuan Wang, Jiayi Ma
Recently, face super-resolution (FSR) methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e. g., facial parsing maps, facial landmarks) to focus on facial structure, thereby maintaining the consistency of the facial structure while restoring facial details.
1 code implementation • CVPR 2021 • Tao Lu, LiMin Wang, Gangshan Wu
Previous point cloud semantic segmentation networks use the same process to aggregate features from neighbors of the same category and different categories.
Ranked #1 on Semantic Segmentation on SYNTHIA
1 code implementation • 5 Jun 2021 • Zhenfeng Shao, JiaMing Wang, Lianbing Deng, Xiao Huang, Tao Lu, Fang Luo, Ruiqian Zhang, Xianwei Lv, Chaoya Dang, Qing Ding, Zhiqiang Wang
In this paper, we introduce a challenging global large-scale ship database (called GLSD), designed specifically for ship detection tasks.
1 code implementation • 24 May 2021 • JiaMing Wang, Zhenfeng Shao, Xiao Huang, Tao Lu, Ruiqian Zhang, Jiayi Ma
Most existing deep learning-based pan-sharpening methods have several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement, we propose a novel pan-sharpening convolutional neural network based on a high-pass modification block.
no code implementations • 23 May 2021 • Zhiqiang Wang, Zhenfeng Shao, Xiao Huang, JiaMing Wang, Tao Lu, Sihang Zhang
In this study, we propose a novel HSI denoising network, termed SSCAN, that combines group convolutions and attention modules.
1 code implementation • 8 May 2021 • JiaMing Wang, Zhenfeng Shao, Tao Lu, Xiao Huang, Ruiqian Zhang, Yu Wang
Despite their success, however, low/high spatial resolution pairs are usually difficult to obtain in satellites with a high temporal resolution, making such approaches in SR impractical to use.
1 code implementation • 18 Apr 2021 • Yuanzhi Wang, Tao Lu, Yanduo Zhang, Yuntao Wu
However, many problems for scene reconversion and shadow estimation tasks, including uncalibrated feature information and poor semantic information, are still unresolved, thereby resulting in insufficient feature representation.
no code implementations • 14 Apr 2021 • Mengan Song, Yiming Huo, Tao Lu, Xiaodai Dong, Zhonghua Liang
As 5G wireless systems and networks are now being globally commercialized and deployed, more diversified application scenarios are emerging, quickly reshaping our societies and paving the road to the beyond 5G (6G) era when terahertz (THz) and unmanned aerial vehicle (UAV) communications may play critical roles.
no code implementations • ICCV 2021 • Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang, Tao Lu, Xin Tian, Jiayi Ma
Most recent video super-resolution (SR) methods either adopt an iterative manner to deal with low-resolution (LR) frames from a temporally sliding window, or leverage the previously estimated SR output to help reconstruct the current frame recurrently.
1 code implementation • 19 Mar 2021 • Kui Jiang, Zhongyuan Wang, Zheng Wang, Chen Chen, Peng Yi, Tao Lu, Chia-Wen Lin
Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps.
no code implementations • 17 Mar 2021 • Ahmed Elmoogy, Xiaodai Dong, Tao Lu, Robert Westendorp, Kishore Reddy
We propose a novel image based localization system using graph neural networks (GNN).
no code implementations • 1 Jan 2021 • Chenghao Liu, Tao Lu, Doyen Sahoo, Yuan Fang, Kun Zhang, Steven Hoi
Meta-learning methods learn the meta-knowledge among various training tasks and aim to promote the learning of new tasks under the task similarity assumption.
no code implementations • 16 Nov 2020 • Boyao Li, Tao Lu, Jiayi Li, Ning Lu, Yinghao Cai, Shuo Wang
Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL).
no code implementations • 7 Nov 2020 • Brosnan Yuen, Minh Tu Hoang, Xiaodai Dong, Tao Lu
This article proposes a Universal Activation Function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems.
1 code implementation • 22 Oct 2020 • Tao Lu, Yuanzhi Wang, Yanduo Zhang, Yu Wang, Wei Liu, Zhongyuan Wang, Junjun Jiang
However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).
no code implementations • 13 May 2020 • Minh Tu Hoang, Brosnan Yuen, Kai Ren, Xiaodai Dong, Tao Lu, Robert Westendorp, Kishore Reddy
This paper proposes a combined network structure between convolutional neural network (CNN) and long-short term memory (LSTM) quantifier for WiFi fingerprinting indoor localization.
no code implementations • 1 Apr 2020 • Bin Wang, Tao Lu, Yanduo Zhang
Comparing with some state-of-the-art SR algorithms with 4$\times$ scale factor, FDSR outperforms the detection performance mAP on MS COCO validation, VOC2007 databases with good generalization to other detection networks.
no code implementations • 8 Jan 2020 • Minh Tu Hoang, Brosnan Yuen, Xiaodai Dong, Tao Lu, Robert Westendorp, Kishore Reddy
In contrast, SSP leverages the information of the previous position to determine the probable location since the user's speed in an indoor environment is bounded and locations near the previous one have higher probability than the other locations.
no code implementations • 25 Sep 2019 • Chenghao Liu, Tao Lu, Doyen Sahoo, Yuan Fang, Steven C.H. Hoi.
Meta-learning methods learn the meta-knowledge among various training tasks and aim to promote the learning of new tasks under the task similarity assumption.
no code implementations • 6 Aug 2019 • Jun Gao, Luyun Gan, Fabiola Buschendorf, Liao Zhang, Hua Liu, Peixue Li, Xiaodai Dong, Tao Lu
We investigate deep learning based omni intrusion detection system (IDS) for supervisory control and data acquisition (SCADA) networks that are capable of detecting both temporally uncorrelated and correlated attacks.
no code implementations • 24 Jun 2019 • Luyun Gan, Brosnan Yuen, Tao Lu
In this paper, we implement multi-label neural networks with optimal thresholding to identify gas species among a multi gas mixture in a cluttered environment.
1 code implementation • 9 May 2019 • Chenghao Liu, Tao Lu, Xin Wang, Zhiyong Cheng, Jianling Sun, Steven C. H. Hoi
However, CF with binary codes naturally suffers from low accuracy due to limited representation capability in each bit, which impedes it from modeling complex structure of the data.
no code implementations • 14 Apr 2019 • Zhe Xin, Yinghao Cai, Tao Lu, Xiaoxia Xing, Shaojun Cai, Jixiang Zhang, Yiping Yang, Yanqing Wang
The fundamental problem of visual place recognition is generating robust image representations which are not only insensitive to environmental changes but also distinguishable to different places.
no code implementations • 27 Mar 2019 • Minh Tu Hoang, Brosnan Yuen, Xiaodai Dong, Tao Lu, Robert Westendorp, Kishore Reddy
This paper proposes recurrent neuron networks (RNNs) for a fingerprinting indoor localization using WiFi.
no code implementations • 19 Mar 2019 • Naijun Liu, Tao Lu, Yinghao Cai, Boyao Li, Shuo Wang
Combining hindsight idea with the generative adversarial imitation learning (GAIL) framework, we realize implementing imitation learning successfully in cases of expert demonstration data are not available.