English
Related papers

Related papers: PointCNN++: Performant Convolution on Native Point…

200 papers

Point cloud is a principal data structure adopted for 3D geometric information encoding. Unlike other conventional visual data, such as images and videos, these irregular points describe the complex shape features of 3D objects, which makes…

Computer Vision and Pattern Recognition · Computer Science 2020-04-21 Chaoyi Zhang , Yang Song , Lina Yao , Weidong Cai

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so…

Computer Vision and Pattern Recognition · Computer Science 2017-05-10 Felix Järemo Lawin , Martin Danelljan , Patrik Tosteberg , Goutam Bhat , Fahad Shahbaz Khan , Michael Felsberg

Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven…

Computer Vision and Pattern Recognition · Computer Science 2020-02-19 Maurice Quach , Giuseppe Valenzise , Frederic Dufaux

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification…

Computer Vision and Pattern Recognition · Computer Science 2019-06-03 Zhuyang Xie , Junzhou Chen , Bo Peng

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network…

Computer Vision and Pattern Recognition · Computer Science 2021-04-12 Shaoshuai Shi , Chaoxu Guo , Li Jiang , Zhe Wang , Jianping Shi , Xiaogang Wang , Hongsheng Li

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Yin Zhou , Oncel Tuzel

We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data autoencoder. To demonstrate its efficiency we learn to synthesize high-resolution point clouds of 10k points that densely describe the underlying geometry of Computer…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Kseniya Cherenkova , Djamila Aouada , Gleb Gusev

LiDAR-based 3D object detection and classification is crucial for autonomous driving. However, real-time inference from extremely sparse 3D data is a formidable challenge. To address this problem, a typical class of approaches transforms…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Yongxin Shao , Aihong Tan , Zhetao Sun , Enhui Zheng , Tianhong Yan , Peng Liao

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical…

Computer Vision and Pattern Recognition · Computer Science 2019-05-17 Shaoshuai Shi , Xiaogang Wang , Hongsheng Li

Recent state-of-the-art methods for point cloud processing are based on the notion of point convolution, for which several approaches have been proposed. In this paper, inspired by discrete convolution in image processing, we provide a…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Alexandre Boulch , Gilles Puy , Renaud Marlet

This paper proposes a computationally efficient approach to detecting objects natively in 3D point clouds using convolutional neural networks (CNNs). In particular, this is achieved by leveraging a feature-centric voting scheme to implement…

Robotics · Computer Science 2017-03-07 Martin Engelcke , Dushyant Rao , Dominic Zeng Wang , Chi Hay Tong , Ingmar Posner

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Zhiyuan Zhang , Binh-Son Hua , David W. Rosen , Sai-Kit Yeung

We present a novel algorithm for point cloud segmentation. Our approach transforms unstructured point clouds into regular voxel grids, and further uses a kernel-based interpolated variational autoencoder (VAE) architecture to encode the…

Graphics · Computer Science 2019-08-21 Hsien-Yu Meng , Lin Gao , YuKun Lai , Dinesh Manocha

Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data. While being able to achieve good accuracies in various scene…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Zhiyuan Zhang , Binh-Son Hua , Sai-Kit Yeung

Over the last decade, the demand for better segmentation and classification algorithms in 3D spaces has significantly grown due to the popularity of new 3D sensor technologies and advancements in the field of robotics. Point-clouds are one…

Computer Vision and Pattern Recognition · Computer Science 2019-10-02 Felipe Gomez Marulanda , Pieter Libin , Timothy Verstraeten , Ann Nowé

Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-10 Zhiyuan Zhang , Binh-Son Hua , Wei Chen , Yibin Tian , Sai-Kit Yeung

In this paper, we investigate the combination of voxel-based methods and point-based methods, and propose a novel end-to-end two-stage 3D object detector named SGNet for point clouds scenes. The voxel-based methods voxelize the scene to…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Hao Peng , Guofeng Tong , Zheng Li , Yaqi Wang , Yuyuan Shao

Channel pruning can effectively reduce both computational cost and memory footprint of the original network while keeping a comparable accuracy performance. Though great success has been achieved in channel pruning for 2D image-based…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Yaomin Huang , Ning Liu , Zhengping Che , Zhiyuan Xu , Chaomin Shen , Yaxin Peng , Guixu Zhang , Xinmei Liu , Feifei Feng , Jian Tang

We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Chaitanya Kaul , Joshua Mitton , Hang Dai , Roderick Murray-Smith

We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Wenxuan Wu , Li Fuxin , Qi Shan