MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

被引:30
作者
Sarode, Vinit [1 ]
Dhagat, Animesh [1 ]
Srivatsan, Rangaprasad Arun [1 ]
Zevallos, Nicolas [1 ]
Lucey, Simon [1 ]
Choset, Howie [1 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
来源
2020 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2020) | 2020年
关键词
REGISTRATION; RANSAC;
D O I
10.1109/3DV50981.2020.00113
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Point clouds have grown in importance in the way computers perceive the world. From LIDAR sensors in autonomous cars and drones to the time of flight and stereo vision systems in our phones, point clouds are everywhere. Despite their ubiquity, point clouds in the real world are often missing points because of sensor limitations or occlusions, or contain extraneous points from sensor noise or artifacts. These problems challenge algorithms that require computing correspondences between a pair of point clouds. Therefore, this paper presents a fully-convolutional neural network that identifies which points in one point cloud are most similar (inliers) to the points in another. We show improvements in learning-based and classical point cloud registration approaches when retrofitted with our network. We demonstrate these improvements on synthetic and real-world datasets. Finally, our network produces impressive results on test datasets that were unseen during training, thus exhibiting generalizability. Code and videos are available at https://github.com/vinits5/masknet
引用
收藏
页码:1029 / 1038
页数:10
相关论文
共 52 条
[21]   SampleNet: Differentiable Point Cloud Sampling [J].
Lang, Itai ;
Manor, Asaf ;
Avidan, Shai .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :7575-7585
[22]   An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells [J].
Li, Lin ;
Yang, Fan ;
Zhu, Haihong ;
Li, Dalin ;
Li, You ;
Tang, Lei .
REMOTE SENSING, 2017, 9 (05)
[23]  
Li YZ, 2018, ADV NEUR IN, V31
[24]   FlowNet3D: Learning Scene Flow in 3D Point Clouds [J].
Liu, Xingyu ;
Qi, Charles R. ;
Guibas, Leonidas J. .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :529-537
[25]   SUPER 4PCS Fast Global Pointcloud Registration via Smart Indexing [J].
Mellado, Nicolas ;
Aiger, Dror ;
Mitra, Niloy J. .
COMPUTER GRAPHICS FORUM, 2014, 33 (05) :205-215
[26]   Point Set Registration: Coherent Point Drift [J].
Myronenko, Andriy ;
Song, Xubo .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (12) :2262-2275
[27]   A ROBUST ESTIMATION TECHNIQUE FOR 3D POINT CLOUD REGISTRATION [J].
Pankaj, Dhanya S. ;
Nidamanuri, Rama Rao .
IMAGE ANALYSIS & STEREOLOGY, 2016, 35 (01) :15-28
[28]  
Qi CR, 2017, ADV NEUR IN, V30
[29]   PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation [J].
Qi, Charles R. ;
Su, Hao ;
Mo, Kaichun ;
Guibas, Leonidas J. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :77-85
[30]   POINTCLEANNET: Learning to Denoise and Remove Outliers from Dense Point Clouds [J].
Rakotosaona, Marie-Julie ;
La Barbera, Vittorio ;
Guerrero, Paul ;
Mitra, Niloy J. ;
Ovsjanikov, Maks .
COMPUTER GRAPHICS FORUM, 2020, 39 (01) :185-203