中文
相关论文

相关论文: PVNet: A Joint Convolutional Network of Point Clou…

200 篇论文

Although convolutional neural networks have achieved remarkable success in analyzing 2D images/videos, it is still non-trivial to apply the well-developed 2D techniques in regular domains to the irregular 3D point cloud data. To bridge this…

计算机视觉与模式识别 · 计算机科学 2020-12-08 Qijian Zhang , Junhui Hou , Yue Qian , Juyong Zhang , Ying He

3D vision with real-time LiDAR-based point cloud data became a vital part of autonomous system research, especially perception and prediction modules use for object classification, segmentation, and detection. Despite their success, point…

计算机视觉与模式识别 · 计算机科学 2023-01-31 Arup Kumar Sarker , Farzana Yasmin Ahmad , Matthew B. Dwyer

In this paper, we address the problem of reconstructing an object's surface from a single image using generative networks. First, we represent a 3D surface with an aggregation of dense point clouds from multiple views. Each point cloud is…

计算机视觉与模式识别 · 计算机科学 2018-11-26 Jinglu Wang , Bo Sun , Yan Lu

Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking…

计算机视觉与模式识别 · 计算机科学 2020-09-29 Xi-An Li , Lei Zhang , Li-Yan Wang , Jian Lu

Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing…

计算机视觉与模式识别 · 计算机科学 2021-07-19 Aoran Xiao , Xiaofei Yang , Shijian Lu , Dayan Guan , Jiaxing Huang

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

计算机视觉与模式识别 · 计算机科学 2019-09-30 Mingtao Feng , Liang Zhang , Xuefei Lin , Syed Zulqarnain Gilani , Ajmal Mian

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Siming Yan , Chen Song , Youkang Kong , Qixing Huang

A laser scanner can easily acquire the geometric data of physical environments in the form of a point cloud. Recognizing objects from a point cloud is often required for industrial 3D reconstruction, which should include not only geometry…

计算机视觉与模式识别 · 计算机科学 2020-07-01 Hyungki Kim , Moohyun Cha , Duhwan Mun

This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Tianyi Lyu , Dian Gu , Peiyuan Chen , Yaoting Jiang , Zhenhong Zhang , Huadong Pang , Li Zhou , Yiping Dong

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation…

计算机视觉与模式识别 · 计算机科学 2021-06-21 Zhijian Qiao , Huanshu Wei , Zhe Liu , Chuanzhe Suo , Hesheng Wang

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…

计算机视觉与模式识别 · 计算机科学 2020-06-09 Liang Du , Xiaoqing Ye , Xiao Tan , Jianfeng Feng , Zhenbo Xu , Errui Ding , Shilei Wen

Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained…

计算机视觉与模式识别 · 计算机科学 2019-01-04 Tong He , Haibin Huang , Li Yi , Yuqian Zhou , Chihao Wu , Jue Wang , Stefano Soatto

Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate information from multiple views. However, the camera view-points…

计算机视觉与模式识别 · 计算机科学 2021-08-18 Abdullah Hamdi , Silvio Giancola , Bernard Ghanem

Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Linlong Fan , Ye Huang , Yanqi Ge , Wen Li , Lixin Duan

Point clouds can be represented in many forms (views), typically, point-based sets, voxel-based cells or range-based images(i.e., panoramic view). The point-based view is geometrically accurate, but it is disordered, which makes it…

计算机视觉与模式识别 · 计算机科学 2021-03-25 Jianyun Xu , Ruixiang Zhang , Jian Dou , Yushi Zhu , Jie Sun , Shiliang Pu

This work considers a new task in geometric deep learning: generating a triangulation among a set of points in 3D space. We present PointTriNet, a differentiable and scalable approach enabling point set triangulation as a layer in 3D…

计算机视觉与模式识别 · 计算机科学 2020-07-24 Nicholas Sharp , Maks Ovsjanikov

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such…

计算机视觉与模式识别 · 计算机科学 2021-07-07 Lifa Zhu , Dongrui Liu , Changwei Lin , Rui Yan , Francisco Gómez-Fernández , Ninghua Yang , Ziyong Feng

Point clouds obtained from 3D scans are typically sparse, irregular, and noisy, and required to be consolidated. In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds.…

计算机视觉与模式识别 · 计算机科学 2018-07-18 Lequan Yu , Xianzhi Li , Chi-Wing Fu , Daniel Cohen-Or , Pheng-Ann Heng

Point cloud is an important type of 3D representation. However, directly applying convolutions on point clouds is challenging due to the sparse, irregular and unordered data structure. In this paper, we propose a novel Interpolated…

计算机视觉与模式识别 · 计算机科学 2019-08-14 Jiageng Mao , Xiaogang Wang , Hongsheng Li

In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously. Firstly, we build an effective…

计算机视觉与模式识别 · 计算机科学 2019-12-23 Lin Zhao , Wenbing Tao