로그인, 회원가입후 더 많은 혜택을 누리세요 로그인 회원가입 닫기
Title:   PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Authors:   Qi, Charles R.Su, HaoMo, KaichunGuibas, Leonidas J.
Publication:   eprint arXiv:1612.00593
Publication Date:   12/2016
Origin:   ARXIV
Keywords:   Computer Science - Computer Vision and Pattern Recognition
Comment:   CVPR 2017
Bibliographic Code:   2016arXiv161200593Q


Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

번호 제목 글쓴이 날짜 조회 수
공지 [공지] 논문 발표 리스트 음파선생 2018.01.26 1531
공지 게시판 자료 복구의 건 음파선생 2017.09.11 139
174 [논문반]Connecting Generative Adversarial Networks and Actor-Critic Methods file 음파선생 2018.01.08 169
» [논문반] PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation file 도니리 2018.01.08 212
172 matrix capsules file 이동훈 2017.12.18 90
171 deep voice 3 file yhlee 2017.12.13 170
170 [논문반] Enhanced Deep Residual Networks for Single Image Super-Resolution file atoz 2017.12.06 154
169 [논문반] Generative Adversarial Networks: An Overview file ilguyi 2017.12.06 731
168 [PR12] Conditional Generative Adversarial Nets file 음파선생 2017.12.03 383
167 [논문반] Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates file 정자민 2017.11.29 87
166 [논문반] Image Captioning and Classification of Dangerous Situations June2374 2017.11.22 112
165 [논문반] Deep Learning for Event-Driven Stock Prediction file 양종열 2017.11.20 744
164 [논문반] DR(eye)VE Project: Predicting Drive's Focus of Attenttion file 도니리 2017.11.15 208
163 look, listen and learn file yhlee 2017.11.13 71
162 [논문반]Spectral Graph Convolutions for Population-based Disease Prediction file Dragon 2017.11.07 99
161 [논문반] Learning From Noisy Large-Scale Datasets With Minimal Supervision 저게뭐니원두막 2017.10.31 100
160 [논문반] Learning by Association_A versatile semi-supervised training file kmsqwet 2017.10.30 64
159 [논문반] InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets file 제발쫌제발 2017.10.24 128
158 [논문반]A Tutorial on Deep Learning for Music Information Retrieval file 음파선생 2017.10.23 512
157 [논문반] EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks file krust 2017.10.16 113
156 [PR12] WaveNet - A Generative Model for Raw Audio file 음파선생 2017.10.15 330
155 [논문반] Faster-RCNN file 박상진 2017.09.25 264