no code implementations • 6 Apr 2024 • Dong Liang, Zhengyan Xu, Ling Li, Mingqiang Wei, Songcan Chen
In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE.
1 code implementation • 7 Mar 2024 • Yihua Fan, Yongzhen Wang, Mingqiang Wei, Fu Lee Wang, Haoran Xie
In this paper, we raise an intriguing question: can the combination of image restoration and object detection enhance detection performance in adverse weather conditions?
no code implementations • 20 Dec 2023 • Lipeng Gu, Xuefeng Yan, Liangliang Nan, Dingkun Zhu, Honghua Chen, Weiming Wang, Mingqiang Wei
The DSE module, designed for real-world autonomous driving scenarios, enhances the semantic perception of point clouds, particularly for distant points.
no code implementations • 8 Dec 2023 • Xin Li, Peng Li, Zeyong Wei, Zhe Zhu, Mingqiang Wei, Junhui Hou, Liangliang Nan, Jing Qin, Haoran Xie, Fu Lee Wang
By performing cross-modal interaction, Cross-BERT can smoothly reconstruct the masked tokens during pretraining, leading to notable performance enhancements for downstream tasks.
1 code implementation • 14 Sep 2023 • Yongyuan Li, Xiuyuan Qin, Chao Liang, Mingqiang Wei
In particular, we propose a Fine-Grained Feature Fusion (FGFF) module to effectively capture fine texture feature information around teeth and surrounding regions, and use these features to fine-grain the feature map to enhance the clarity of teeth.
1 code implementation • ICCV 2023 • Zhe Zhu, Honghua Chen, Xing He, Weiming Wang, Jing Qin, Mingqiang Wei
In this paper, we propose a novel network, SVDFormer, to tackle two specific challenges in point cloud completion: understanding faithful global shapes from incomplete point clouds and generating high-accuracy local structures.
no code implementations • 21 Apr 2023 • Chengyu Zheng, Peng Li, Xiao-Ping Zhang, Xuequan Lu, Mingqiang Wei
The IS is designed to simulate the detection procedure of human recognition for identifying transparent glass by global context and edge information.
1 code implementation • 31 Mar 2023 • Yongzhen Wang, Xuefeng Yan, Yanbiao Niu, Lina Gong, Yanwen Guo, Mingqiang Wei
In this study, we propose an effective image deraining paradigm for Mixture of rain REmoval, called DEMore-Net, which takes full account of the MOR effect.
no code implementations • 24 Mar 2023 • Mingqiang Wei, Qian Sun, Haoran Xie, Dong Liang, Fu Lee Wang
Searching by image is popular yet still challenging due to the extensive interference arose from i) data variations (e. g., background, pose, visual angle, brightness) of real-world captured images and ii) similar images in the query dataset.
no code implementations • 23 Mar 2023 • Yun Liu, Xuefeng Yan, Zhilei Chen, Zhiqi Li, Zeyong Wei, Mingqiang Wei
Self-supervised learning is attracting large attention in point cloud understanding.
1 code implementation • CVPR 2023 • Shanshan Li, Pan Gao, Xiaoyang Tan, Mingqiang Wei
Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies.
no code implementations • 30 Jan 2023 • Xin Li, Mingqiang Wei, Songcan Chen
From the perspective of how-and-what-to-learn, PointSmile is designed to imitate human curriculum learning, i. e., starting with an easy curriculum and gradually increasing the difficulty of that curriculum.
no code implementations • 23 Jan 2023 • Mingqiang Wei, Yiyang Shen, Yongzhen Wang, Haoran Xie, Jing Qin, Fu Lee Wang
Before answering it, we observe two major obstacles of diffusion models in real-world image deraining: the need for paired training data and the limited utilization of multi-scale rain patterns.
no code implementations • 17 Nov 2022 • Yiyang Shen, Rongwei Yu, Peng Wu, Haoran Xie, Lina Gong, Jing Qin, Mingqiang Wei
We propose ImLiDAR, a new 3OD paradigm to narrow the cross-sensor discrepancies by progressively fusing the multi-scale features of camera Images and LiDAR point clouds.
no code implementations • 3 Nov 2022 • Lipeng Gu, Xuefeng Yan, Peng Cui, Lina Gong, Haoran Xie, Fu Lee Wang, Jin Qin, Mingqiang Wei
There is a trend to fuse multi-modal information for 3D object detection (3OD).
no code implementations • 29 Oct 2022 • Zhiheng Hu, Yongzhen Wang, Peng Li, Jie Qin, Haoran Xie, Mingqiang Wei
First, to maintain small targets in deep layers, we develop a multi-scale nested interaction module to explore a wide range of context information.
no code implementations • 28 Oct 2022 • Huajian Si, Zeyong Wei, Zhe Zhu, Honghua Chen, Dong Liang, Weiming Wang, Mingqiang Wei
Bilateral filter (BF) is a fast, lightweight and effective tool for image denoising and well extended to point cloud denoising.
no code implementations • 28 Oct 2022 • Zhaowei Chen, Peng Li, Zeyong Wei, Honghua Chen, Haoran Xie, Mingqiang Wei, Fu Lee Wang
We propose GeoGCN, a novel geometric dual-domain graph convolution network for point cloud denoising (PCD).
no code implementations • 28 Oct 2022 • Ming Tong, Yongzhen Wang, Peng Cui, Xuefeng Yan, Mingqiang Wei
Semi-UFormer can well leverage both the real-world hazy images and their uncertainty guidance information.
no code implementations • 28 Oct 2022 • Baian Chen, Lipeng Gu, Xin Zhuang, Yiyang Shen, Weiming Wang, Mingqiang Wei
We propose PSFormer, an effective point transformer model for 3D salient object detection.
4 code implementations • 5 Sep 2022 • Fei Hu, Honghua Chen, Xuequan Lu, Zhe Zhu, Jun Wang, Weiming Wang, Fu Lee Wang, Mingqiang Wei
We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings.
1 code implementation • 3 Sep 2022 • Yongzhen Wang, Xuefeng Yan, Kaiwen Zhang, Lina Gong, Haoran Xie, Fu Lee Wang, Mingqiang Wei
Adverse weather conditions such as haze, rain, and snow often impair the quality of captured images, causing detection networks trained on normal images to generalize poorly in these scenarios.
1 code implementation • 2 Sep 2022 • Jie Wang, Yongzhen Wang, Yidan Feng, Lina Gong, Xuefeng Yan, Haoran Xie, Fu Lee Wang, Mingqiang Wei
Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details.
no code implementations • 2 Sep 2022 • Honghua Chen, Mingqiang Wei, Jun Wang
In this work, we provide a comprehensive review of the advances in mesh denoising, containing both traditional geometric approaches and recent learning-based methods.
no code implementations • 31 Aug 2022 • Baian Chen, Liangliang Nan, Haoran Xie, Dening Lu, Fu Lee Wang, Mingqiang Wei
Capturing both local and global features of irregular point clouds is essential to 3D object detection (3OD).
1 code implementation • 30 Aug 2022 • Anyi Huang, Qian Xie, Zhoutao Wang, Dening Lu, Mingqiang Wei, Jun Wang
Second, a multi-scale perception module is designed to embed multi-scale geometric information for each scale feature and regress multi-scale weights to guide a multi-offset denoising displacement.
no code implementations • 29 Aug 2022 • Peng Wu, Lipeng Gu, Xuefeng Yan, Haoran Xie, Fu Lee Wang, Gary Cheng, Mingqiang Wei
Such a module will guide our PV-RCNN++ to integrate more object-related point-wise and voxel-wise features in the pivotal areas.
no code implementations • 17 Aug 2022 • Haoran Pan, Jun Zhou, Yuanpeng Liu, Xuequan Lu, Weiming Wang, Xuefeng Yan, Mingqiang Wei
The SO(3)-equivariant features communicate with RGB features to deduce the (missed) geometry for detecting keypoints of an object with the reflective surface from the depth channel.
1 code implementation • 4 Aug 2022 • Zhilei Chen, Honghua Chen, Lina Gong, Xuefeng Yan, Jun Wang, Yanwen Guo, Jing Qin, Mingqiang Wei
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner.
no code implementations • 1 Aug 2022 • Zhe Zhu, Liangliang Nan, Haoran Xie, Honghua Chen, Mingqiang Wei, Jun Wang, Jing Qin
The first module transfers the intrinsic shape characteristics from single images to guide the geometry generation of the missing regions of point clouds, in which we propose IPAdaIN to embed the global features of both the image and the partial point cloud into completion.
Ranked #2 on Point Cloud Completion on ShapeNet-ViPC
1 code implementation • 14 Jul 2022 • Chen Chen, Yisen Wang, Honghua Chen, Xuefeng Yan, Dayong Ren, Yanwen Guo, Haoran Xie, Fu Lee Wang, Mingqiang Wei
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding. Despite of significant advances in recent years, most of existing methods still suffer from either the object-level misclassification or the boundary-level ambiguity.
no code implementations • 2 Jul 2022 • Honghua Chen, Zeyong Wei, Yabin Xu, Mingqiang Wei, Jun Wang
Low-overlap regions between paired point clouds make the captured features very low-confidence, leading cutting edge models to point cloud registration with poor quality.
no code implementations • 20 Jun 2022 • Baian Chen, Zhilei Chen, Xiaowei Hu, Jun Xu, Haoran Xie, Mingqiang Wei, Jing Qin
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring the long-range semantic contexts and geometric information on both RGB and depth features to infer salient objects.
1 code implementation • 9 Jun 2022 • Mingqiang Wei, Zeyong Wei, Haoran Zhou, Fei Hu, Huajian Si, Zhilei Chen, Zhe Zhu, Jingbo Qiu, Xuefeng Yan, Yanwen Guo, Jun Wang, Jing Qin
In this paper, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis.
no code implementations • 3 Jun 2022 • Qiqi Ding, Peng Li, Xuefeng Yan, Ding Shi, Luming Liang, Weiming Wang, Haoran Xie, Jonathan Li, Mingqiang Wei
To our knowledge, RSOD is the first quantitatively evaluated and graded snowy OD dataset.
no code implementations • 16 May 2022 • Dening Lu, Qian Xie, Mingqiang Wei, Kyle Gao, Linlin Xu, Jonathan Li
To demonstrate the superiority of Transformers in point cloud analysis, we present comprehensive comparisons of various Transformer-based methods for classification, segmentation, and object detection.
1 code implementation • 4 May 2022 • Yongzhen Wang, Xuefeng Yan, Fu Lee Wang, Haoran Xie, Wenhan Yang, Mingqiang Wei, Jing Qin
From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus bridging the gap between synthetic and real-world haze is avoided.
1 code implementation • 28 Apr 2022 • Yiyang Shen, Yongzhen Wang, Mingqiang Wei, Honghua Chen, Haoran Xie, Gary Cheng, Fu Lee Wang
Rain is one of the most common weather which can completely degrade the image quality and interfere with the performance of many computer vision tasks, especially under heavy rain conditions.
1 code implementation • 6 Apr 2022 • Yiyang Shen, Mingqiang Wei, Sen Deng, Wenhan Yang, Yongzhen Wang, Xiao-Ping Zhang, Meng Wang, Jing Qin
To bridge the two domain gaps, we propose a semi-supervised detail-recovery image deraining network (Semi-DRDNet) with dual sample-augmented contrastive learning.
no code implementations • 2 Apr 2022 • Zeyong Wei, Honghua Chen, Hao Tang, Qian Xie, Mingqiang Wei, Jun Wang
The shape of circle is one of fundamental geometric primitives of man-made engineering objects.
no code implementations • 29 Mar 2022 • Yuwen Deng, Donghai Guan, Yanyu Chen, Weiwei Yuan, Jiemin Ji, Mingqiang Wei
This paper studies a practically meaningful ship detection problem from synthetic aperture radar (SAR) images by the neural network.
1 code implementation • 23 Mar 2022 • Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lu, Jing Qin, Xiao-Ping Zhang
Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations.
no code implementations • 5 Mar 2022 • Yidan Feng, Biqi Yang, Xianzhi Li, Chi-Wing Fu, Rui Cao, Kai Chen, Qi Dou, Mingqiang Wei, Yun-hui Liu, Pheng-Ann Heng
Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances.
1 code implementation • 1 Mar 2022 • Fu Lee Wang, Yidan Feng, Haoran Xie, Gary Cheng, Mingqiang Wei
Image filters are fast, lightweight and effective, which make these conventional wisdoms preferable as basic tools in vision tasks.
1 code implementation • Computer-Aided Design 2022 • Yingkui Zhang, Guibao Shen, Qiong Wang, Yinling Qian, Mingqiang Wei, Jing Qin
For the first time, we optimize both positions and normals (i. e., dual domains) in a unified framework of GNN, and show the powerful inter-coordination between the dual domains.
1 code implementation • 13 Dec 2021 • Dong Liang, Ling Li, Mingqiang Wei, Shuo Yang, Liyan Zhang, Wenhan Yang, Yun Du, Huiyu Zhou
Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images.
1 code implementation • 13 Dec 2021 • Dong Liang, Qixiang Geng, Zongqi Wei, Dmitry A. Vorontsov, Ekaterina L. Kim, Mingqiang Wei, Huiyu Zhou
On DOTA, our DEA-Net which integrated with the baseline of RoI-Transformer surpasses the advanced method by 0. 40% mean-Average-Precision (mAP) for oriented object detection with a weaker backbone network (ResNet-101 vs ResNet-152) and 3. 08% mean-Average-Precision (mAP) for horizontal object detection with the same backbone.
Ranked #15 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • ICCV 2021 • Haoran Zhou, Yidan Feng, Mingsheng Fang, Mingqiang Wei, Jing Qin, Tong Lu
Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect.
Ranked #10 on 3D Point Cloud Classification on IntrA
no code implementations • 15 Jun 2021 • Sen Deng, Yidan Feng, Mingqiang Wei, Haoran Xie, Yiping Chen, Jonathan Li, Xiao-Ping Zhang, Jing Qin
Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image.
1 code implementation • 21 Mar 2021 • Zongqi Wei, Dong Liang, Dong Zhang, Liyan Zhang, Qixiang Geng, Mingqiang Wei, Huiyu Zhou
Specifically, for a given set of feature maps, CG first computes the feature similarity between each channel and the remaining channels as the intermediary calibration guidance.
no code implementations • ICCV 2021 • Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Dening Lu, Mingqiang Wei, Jun Wang
Hough voting, as has been demonstrated in VoteNet, is effective for 3D object detection, where voting is a key step.
no code implementations • 21 May 2020 • Yiyang Shen, Yidan Feng, Sen Deng, Dong Liang, Jing Qin, Haoran Xie, Mingqiang Wei
We observe three intriguing phenomenons that, 1) rain is a mixture of raindrops, rain streaks and rainy haze; 2) the depth from the camera determines the degrees of object visibility, where objects nearby and faraway are visually blocked by rain streaks and rainy haze, respectively; and 3) raindrops on the glass randomly affect the object visibility of the whole image space.
1 code implementation • 27 Aug 2019 • Sen Deng, Mingqiang Wei, Jun Wang, Luming Liang, Haoran Xie, Meng Wang
We have validated our approach on four recognized datasets (three synthetic and one real-world).
1 code implementation • 18 Aug 2019 • Luming Liang, Sen Deng, Lionel Gueguen, Mingqiang Wei, Xinming Wu, Jing Qin
We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise.