Learning to Sample
The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Processing large point clouds is a challenging task. Therefore, the data is often sampled to a size that can be processed more easily. The question is how to sample the data? A popular sampling technique is Farthest Point Sampling (FPS). However, FPS is agnostic to a downstream application (classification, retrieval, etc.). The underlying assumption seems to be that minimizing the farthest point distance, as done by FPS, is a good proxy to other objective functions. We show that it is better to learn how to sample. To do that, we propose a deep network to simplify 3D point clouds. The network, termed S-NET, takes a point cloud and produces a smaller point cloud that is optimized for a particular task. The simplified point cloud is not guaranteed to be a subset of the original point cloud. Therefore, we match it to a subset of the original points in a post-processing step. We contrast our approach with FPS by experimenting on two standard data sets and show significantly better results for a variety of applications. Our code is publicly available.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles, R. Q., Su, H., Kaichun, M., & Guibas, L. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.16 · Cited by 9,237 · cited 7×
“Similar to their previous work [27], FPS was used for evaluating the ability of their network to operate on fewer input points.”
BackgroundMethodInfluentialWrappers for feature subset selection
Kohavi, R., & John, G. H. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(97)00043-x · Cited by 8,947 · cited 1×
“Our approach can be thought of as a feature selection mechanism [9, 16].”
BackgroundAn introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
Dynamic Graph CNN for Learning on Point Clouds
Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019) · ACM Transactions on Graphics · doi:10.1145/3326362 · Cited by 7,199 · cited 1×
“Among various applications one can find point cloud classification [27, 28, 21, 42, 30, 36], part segmentation [27, 28, 21, 30, 36, 20], semantic segmentation [27, 21, 36, 34, 32, 12] and retrieval [35, 17].”
BackgroundAn Introduction to Variable and Feature Selection.
Guyon, I., & Elisseeff, A. (2003) · Cited by 6,576
3D ShapeNets: A deep representation for volumetric shapes
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298801 · Cited by 4,550 · cited 5×
“We report instance classification results on the ModelNet40 data set, adopting the official train-test split.”
MethodInfluentialHoppe, H. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237216 · Cited by 2,817 · cited 1×
“Progressive simplification In a seminal paper, Hoppe [11] proposed a technique for progressive mesh simplification.”
MethodRecurrent Models of Visual Attention
Mnih, V., Heess, N., Graves, A., & Kavukcuoglu, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6247 · Cited by 2,568 · cited 1×
“It can also be interpreted as a form of visual attention [22, 14], focusing the subsequent task network on the significant points.”
BackgroundA Point Set Generation Network for 3D Object Reconstruction from a Single Image
Fan, H., Su, H., & Guibas, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.264 · Cited by 2,402 · cited 4×
“A widely used approach for matching two point sets is the Earth Mover’s Distance (EMD) [1, 41, 43, 7].”
BackgroundMethodInfluentialShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2015) · arXiv · doi:10.48550/arxiv.1512.03012 · Cited by 2,330 · cited 1×
“For reconstruction we employ ShapeNet Core55 repository [4] and the point set autoencoder of Achlioptas et al.”
MethodShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T. A., Guibas, L. J., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2023) · doi:10.5281/zenodo.10089705 · Cited by 1,623
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
Yang, Y., Feng, C., Shen, Y., & Tian, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00029 · Cited by 1,313 · cited 1×
“Other techniques perform point cloud auto-encoding [1, 38, 8], generation [1, 33, 19], completion [1, 2, 41] and up-sampling [40, 39, 43].”
MethodYuan, W., Khot, T., Held, D., Mertz, C., & Hebert, M. (2018) · 2018 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00088 · Cited by 998
SO-Net: Self-Organizing Network for Point Cloud Analysis
Li, J., Chen, B. M., & Lee, G. H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00979 · Cited by 985
SEGCloud: Semantic Segmentation of 3D Point Clouds
Tchapmi, L., Choy, C., Armeni, I., Gwak, J., & Savarese, S. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00067 · Cited by 826
Multiple Object Recognition with Visual Attention
Ba, J., Mnih, V., & Kavukcuoglu, K. (2014) · arXiv · doi:10.48550/arxiv.1412.7755 · Cited by 808 · cited 1×
“It can also be interpreted as a form of visual attention [22, 14], focusing the subsequent task network on the significant points.”
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Su, H., Jampani, V., Sun, D., Maji, S., Kalogerakis, E., Yang, M.-H., & Kautz, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00268 · Cited by 797
MeshCNN: a network with an edge
Hanocka, R., Hertz, A., Fish, N., Giryes, R., Fleishman, S., & Cohen-Or, D. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322959 · Cited by 742
PU-Net: Point Cloud Upsampling Network
Yu, L., Li, X., Fu, C.-W., Cohen-Or, D., & Heng, P.-A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00295 · Cited by 697
The farthest point strategy for progressive image sampling
Eldar, Y., Lindenbaum, M., Porat, M., & Zeevi, Y. Y. (1997) · IEEE Transactions on Image Processing · doi:10.1109/83.623193 · Cited by 693
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
Uy, M. A., & Lee, G. H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00470 · Cited by 670
Pointwise Convolutional Neural Networks
Hua, B.-S., Tran, M.-K., & Yeung, S.-K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00109 · Cited by 615
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
Shen, Y., Feng, C., Yang, Y., & Tian, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00478 · Cited by 532 · cited 1×
“Among various applications one can find point cloud classification [27, 28, 21, 42, 30, 36], part segmentation [27, 28, 21, 30, 36, 20], semantic segmentation [27, 21, 36, 34, 32, 12] and retrieval [35, 17].”
BackgroundAtlasNet: A Papier-Mâché Approach to Learning 3D Surface GenerationPreprint
Groueix, T., Fisher, M., Kim, V. G., Russell, B. C., & Aubry, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.05384 · Cited by 411
Alexa, M., Behr, J., Cohen-Or, D., Fleishman, S., Levin, D., & Silva, C. T. (2005) · Proceedings Visualization, 2001. VIS '01. · doi:10.1109/visual.2001.964489 · Cited by 332 · cited 1×
“These sampling methods, as well as other approaches in the literature [6, 7], operate according to a non-learned predetermined rule.”
MethodEC-Net: An Edge-Aware Point Set Consolidation Network
Yu, L., Li, X., Fu, C.-W., Cohen-Or, D., & Heng, P.-A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_24 · Cited by 300
Fast Resampling of Three-Dimensional Point Clouds via Graphs
Chen, S., Tian, D., Feng, C., Vetro, A., & Kovacevic, J. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2771730 · Cited by 183 · cited 2×
“[5] employed graph-based filters to extract per point features.”
BackgroundMethodPointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention
Sun, Y., Wang, Y., Liu, Z., Siegel, J. E., & Sarma, S. E. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093430 · Cited by 175 · cited 1×
“Other techniques perform point cloud auto-encoding [1, 38, 8], generation [1, 33, 19], completion [1, 2, 41] and up-sampling [40, 39, 43].”
MethodHigh Fidelity Semantic Shape Completion for Point Clouds Using Latent Optimization
Gurumurthy, S., & Agrawal, S. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00122 · Cited by 47
Data-driven Upsampling of Point Clouds
Zhang, W., Jiang, H., Yang, Z., et al. (2019) · Computer-Aided Design · doi:10.1016/j.cad.2019.02.006 · Cited by 32
Deep Point Convolutional Approach for 3D Model Retrieval
Kuang, Z., Yu, J., Jianping Fan, B., & Tan, M. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486479 · Cited by 8 · cited 1×
“Among various applications one can find point cloud classification [27, 28, 21, 42, 30, 36], part segmentation [27, 28, 21, 30, 36, 20], semantic segmentation [27, 21, 36, 34, 32, 12] and retrieval [35, 17].”
Background
Cited by
Zhao, H., Jiang, L., Jia, J., Torr, P., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01595 · Cited by 2,476
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., & Markham, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01112 · Cited by 2,275
PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows
Yang, G., Huang, X., Hao, Z., Liu, M.-Y., Belongie, S., & Hariharan, B. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00464 · Cited by 656
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Xu, C., Wu, B., Wang, Z., Zhan, W., Vajda, P., Keutzer, K., & Tomizuka, M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58604-1_1 · Cited by 430
Metadata
- Authors
- Dovrat, O., Lang, I., & Avidan, S.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 2755-2764
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2963094037
- Cited by
- 183
- References
- 31
- FWCI
- 25.25
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.