Point Cloud Analysis - Must Reading

We have presented a novel approach for point cloud completion, which completes the partial point cloud in two stages

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

Weibo

Cited by23BibtexViews140Links

Chibane Julian,Alldieck Thiemo,Pons-Moll Gerard

CVPR, pp.6968-6979, (2020)

While many works focus on 3D reconstruction from images, in this paper, we focus on 3D shape reconstruction and completion from a variety of 3D inputs, which are deficient in some respect: low and high resolution voxels, sparse and dense point clouds, complete or incomplete

TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

Weibo

Cited by9BibtexViews33Links

Zhe Liu, Xin Zhao,Tengteng Huang, Hu Ruolan, Yu Zhou,Xiang Bai

AAAI, pp.11677-11684, (2020)

This paper proposes a novel Triple Attention Network for 3D object detection in point clouds, especially for noising point clouds

ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes

Weibo

Cited by4BibtexViews30Links

Qi Charles R.,Chen Xinlei,Litany Or,Guibas Leonidas J.

CVPR, pp.4403-4412, (2020)

In this work we have explored how image data can assist a voting-based 3D detection pipeline

Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

Weibo

Cited by3BibtexViews103Links

Mingye Xu, Zhipeng Zhou,Yu Qiao

AAAI, pp.12500-12507, (2020)

Experiments have shown that Geometry Sharing Network achieves the state-of-the-art performance and has robustness to geometric transformations

Learning multiview 3D point cloud registration

Weibo

Cited by2BibtexViews17Links

Gojcic Zan,Zhou Caifa,Wegner Jan D.,Guibas Leonidas J.,Birdal Tolga

CVPR, pp.1756-1766, (2020)

Research on local descriptors for pairwise registration of 3D point clouds is centered on deep learning approaches that succeed in capturing and encoding evidence hidden to hand-engineered descriptors

Grid-GCN for Fast and Scalable Point Cloud Learning

Weibo

Cited by2BibtexViews70Links

Qiangeng Xu,Xudong Sun,Cho-Ying Wu,Panqu Wang,Ulrich Neumann

CVPR, pp.5660-5669, (2020)

We propose Grid-graph convolutional networks for fast and scalable point cloud learning

PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

Weibo

Cited by1BibtexViews21Links

Li Ruihui,Li Xianzhi,Heng Pheng-Ann,Fu Chi-Wing

CVPR, pp.6377-6386, (2020)

We presented PointAugment, the first auto-augmentation framework that we are aware of for 3D point clouds, considering both the capability of the classification network and the complexity of the training samples

Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences

Weibo

Cited by1BibtexViews48Links

Xiaoshui Huang,Guofeng Mei,Jian Zhang

CVPR, pp.11363-11371, (2020)

We propose a feature-metric framework to solve the point cloud registration, and the framework can be trained using a semi-supervised or unsupervised manner

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

Weibo

Cited by0BibtexViews37Links

Xie Qian,Lai Yu-Kun,Wu Jing, Wang Zhoutao, Zhang Yiming,Xu Kai,Wang Jun

CVPR, pp.10444-10453, (2020)

It is even difficult for humans to recognize the objects in the scene when merely a 3D point cloud is given without any color information

PF-Net: Point Fractal Network for 3D Point Cloud Completion

Weibo

Cited by0BibtexViews74Links

Huang Zitian, Yu Yikuan, Xu Jiawen,Ni Feng,Le Xinyi

CVPR, pp.7659-7667, (2020)

Single-resolution Multi-Layer Perception consists of 5 layers Multi-Layer Perception and 2 linear layers, each layer followed by batch normalization and ReLU activation

Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling

Weibo

Cited by0BibtexViews14Links

Wenkai Han,Chenglu Wen,Cheng Wang, Xin Li, Qing Li

AAAI, pp.10925-10932, (2020)

We present a novel framework, Point2Node, for correlation learning among 3D points

MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignment

Weibo

Cited by0BibtexViews15Links

Bernard Florian,Suri Zeeshan Khan,Theobalt Christian

CVPR, pp.13823-13832, (2020)

We present a convex mixed-integer programming formulation for non-rigid shape matching

PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding

Weibo

Cited by0BibtexViews34Links

Saining Xie, Jiatao Gu, Demi Guo,Charles R. Qi,Leonidas J. Guibas,Or Litany

european conference on computer vision, pp.574-591, (2020)

We have demonstrated an extensive evaluation of the transferability of learned representations in 3D point clouds to high-level 3D understanding tasks

DPDist : Comparing Point Clouds Using Deep Point Cloud Distance

Weibo

Cited by0BibtexViews69Links

Urbach Dahlia, Ben-Shabat Yizhak, Lindenbaum Michael

european conference on computer vision, pp.545-560, (2020)

The Deep Point Cloud Distance method is based on estimating the distances of points from one cloud to the underlying continuous surface corresponding to the other point cloud

DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares

Weibo

Cited by0BibtexViews5Links

Ben-Shabat Yizhak,Gould Stephen

european conference on computer vision, pp.20-34, (2020)

In this paper we presented a novel method for deep surface fitting for unstructured 3D point clouds

PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation

Weibo

Cited by0BibtexViews10Links

Haojie Liu, Kang Liao,Chunyu Lin,Yao Zhao,Meiqin Liu

Sensors, no. 6 (2020): 1573

The bidirectional optical flow explicitly guides consecutive sparse depth maps to generate an intermediate depth map, which is further improved by the warping layer

nuScenes: A multimodal dataset for autonomous driving

Weibo

Cited by0BibtexViews13Links

Holger Caesar, Varun Bankiti,Alex H. Lang,Sourabh Vora,Venice Erin Liong, Qiang Xu,Anush Krishnan, Yu Pan,Giancarlo Baldan,Oscar Beijbom

CVPR 2020, (2019)

This is the first dataset collected from an AV approved for testing on public roads and that contains the full 360◦ sensor suite. nuScenes has the largest collection of 3D box annotations of any previously released dataset

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

Weibo

Cited by192BibtexViews59Links

Shaoshuai Shi,Xiaogang Wang,Hongsheng Li

CVPR, (2019): 770-779

The stage-2 network refines the proposals in the canonical coordinate by combining semantic features and local spatial features

PointPillars: Fast Encoders for Object Detection from Point Clouds

Weibo

Cited by186BibtexViews69Links

Alex H. Lang,Sourabh Vora,Holger Caesar,Lubing Zhou, Jiong Yang,Oscar Beijbom

CVPR, (2019): 12697-12705

We introduce PointPillars, a novel deep network and encoder that can be trained end-to-end on lidar point clouds