57 citations · 252 across the 48 of their papers we have counts for
29 papers · 2 filters
ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection
Yiyang Shen, Rongwei Yu, Peng Wu +4
LiDAR and camera, as two different sensors, supply geometric (point clouds) and semantic (RGB images) information of 3D scenes. However, it is still challenging for existing method…
PointSee: Image Enhances Point Cloud
Lipeng Gu, Xuefeng Yan, Peng Cui +5
There is a trend to fuse multi-modal information for 3D object detection (3OD). However, the challenging problems of low lightweightness, poor flexibility of plug-and-play, and ina…
Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing
Ming Tong, Yongzhen Wang, Peng Cui +2
Image dehazing is fundamental yet not well-solved in computer vision. Most cutting-edge models are trained in synthetic data, leading to the poor performance on real-world hazy sce…
LBF:Learnable Bilateral Filter For Point Cloud Denoising
Huajian Si, Zeyong Wei, Zhe Zhu +4
Bilateral filter (BF) is a fast, lightweight and effective tool for image denoising and well extended to point cloud denoising. However, it often involves continual yet manual para…
PSFormer: Point Transformer for 3D Salient Object Detection
Baian Chen, Lipeng Gu, Xin Zhuang +3
We propose PSFormer, an effective point transformer model for 3D salient object detection. PSFormer is an encoder-decoder network that takes full advantage of transformers to model…
GeoGCN: Geometric Dual-domain Graph Convolution Network for Point Cloud Denoising
Zhaowei Chen, Peng Li, Zeyong Wei +4
We propose GeoGCN, a novel geometric dual-domain graph convolution network for point cloud denoising (PCD). Beyond the traditional wisdom of PCD, to fully exploit the geometric inf…
iSmallNet: Densely Nested Network with Label Decoupling for Infrared Small Target Detection
Zhiheng Hu, Yongzhen Wang, Peng Li +3
Small targets are often submerged in cluttered backgrounds of infrared images. Conventional detectors tend to generate false alarms, while CNN-based detectors lose small targets in…
SPCNet: Stepwise Point Cloud Completion Network
Fei Hu, Honghua Chen, Xuequan Lu +5
How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate th…
TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning
Yongzhen Wang, Xuefeng Yan, Kaiwen Zhang +4
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 the…
Contrastive Semantic-Guided Image Smoothing Network
Jie Wang, Yongzhen Wang, Yidan Feng +5
Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details. Deep learning has been explored in…
MODNet: Multi-offset Point Cloud Denoising Network Customized for Multi-scale Patches
Anyi Huang, Qian Xie, Zhoutao Wang +3
The intricacy of 3D surfaces often results cutting-edge point cloud denoising (PCD) models in surface degradation including remnant noise, wrongly-removed geometric details. Althou…
UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration
Zhilei Chen, Honghua Chen, Lina Gong +5
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inh…
3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning
Baian Chen, Liangliang Nan, Haoran Xie +3
Capturing both local and global features of irregular point clouds is essential to 3D object detection (3OD). However, mainstream 3D detectors, e.g., VoteNet and its variants, eith…
PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection
Peng Wu, Lipeng Gu, Xuefeng Yan +4
Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing…
SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation
Haoran Pan, Jun Zhou, Yuanpeng Liu +4
6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complem…
CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion
Zhe Zhu, Liangliang Nan, Haoran Xie +4
How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, a…
GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling
Chen Chen, Yisen Wang, Honghua Chen +6
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…
ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs
Honghua Chen, Zeyong Wei, Yabin Xu +2
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. Beyond th…
Dynamic Message Propagation Network for RGB-D Salient Object Detection
Baian Chen, Zhilei Chen, Xiaowei Hu +4
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…
CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset
Qiqi Ding, Peng Li, Xuefeng Yan +6
Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also…
AGConv: Adaptive Graph Convolution on 3D Point Clouds
Mingqiang Wei, Zeyong Wei, Haoran Zhou +9
Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences ind…
UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning
Yongzhen Wang, Xuefeng Yan, Fu Lee Wang +4
While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known d…
Transformers in 3D Point Clouds: A Survey
Dening Lu, Qian Xie, Mingqiang Wei +3
Transformers have been at the heart of the Natural Language Processing (NLP) and Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring the use…
Deep Algebraic Fitting for Multiple Circle Primitives Extraction from Raw Point Clouds
Zeyong Wei, Honghua Chen, Hao Tang +3
The shape of circle is one of fundamental geometric primitives of man-made engineering objects. Thus, extraction of circles from scanned point clouds is a quite important task in 3…