Skip to content

Latest commit

 

History

History
168 lines (89 loc) · 5.78 KB

3D_Point_Cloud_Paper.md

File metadata and controls

168 lines (89 loc) · 5.78 KB
Raw

Point Cloud PaperList

目录

Point-based networks

pointnets

  • DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds.(arxiv 2019)

  • MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds.(arxiv 2019)

  • Discrete Rotation Equivariance for Point Cloud Recognition.(ICRA 2019)

  • Generalizing discrete convolutions for unstructured point clouds.(arxiv 2019)

  • Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions.(2019 Technical report)

  • 3D Local Features for Direct Pairwise Registration.(CVPR 2019)

  • Dynamic graph cnn for learning on point clouds.(arxiv 2018)

  • Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling(CVPR 2018)

  • Pointwise convolutional neural networks.(CVPR 2018)

  • PointCNN.(NIPS 2018)

  • PointSIFT: A SIFT-like network module for 3D point cloud semantic segmentation.(arxiv 2018)

  • Multiresolution tree networks for 3D point cloud processing.(ECCV 2018)

  • Fully-convolutional point networks for large-scale point clouds.(ECCV 2018)

  • PointNet: Deep learning on point sets for 3D classification and segmentation.(CVPR 2017)

  • PointNet++: Deep hierarchical feature learning on point sets in a metric space.(NIPS 2017)

point cloud compression and representation

  • Point2Sequence: Learning the shape representation of 3D point clouds with an attention-based sequence to sequence network.（ACCV 2019)

  • Adaptive OCNN: A patch-based deep representation of 3D shapes(TOG 2018)

  • Escape from cells: deep KdNetworks for the recognition of 3D point cloud models.(ICCV 2017)

  • OctNet: Learning deep 3D representations at high resolutions.(CVPR 2017)

volumetric methods

  • Shape completion using 3DEncoderPredictor CNNs and shape synthesis.(CVPR 2017)

  • OctNet: Learning deep 3D representations at high resolutions.(CVPR 2017)

  • Voxnet: A 3D convolutional neural network for real*time object recognition.(IROS 2015)

  • 3D ShapeNets: A deep representation for volumetric shapes.(CVPR 2015)

geometric deep learning

  • Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs.(CVPR 2017)

  • Geodesic convolutional neural networks on Riemannian manifolds.(ICCV 2015)

  • Spectral networks and locally connected networks on graphs.(ICLR 2014)

Sample

  • Learning to Sample.(CVPR 2019)

  • Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling.(CVPR 2019)

  • Ecnet: an edge-aware point set consolidation network.(ECCV 2018)

  • Data-driven upsampling of point clouds.(arxiv 2018)

  • Pointgrow: Autoregressively learned point cloud generation with self-attention.(arxiv 2018)

  • PU-Net: Point Cloud Upsampling Network.(CVPR 2018)

  • Deep points consolidation.(TOG 2015)

  • Edge-aware point set resampling.(TOG 2013)

Generation

Auto-Encoder method

  • Revealing Scenes by Inverting Structure from Motion Reconstructions.(CVPR 2019)

  • FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation.(CVPR 2018)

Adversarial method

  • Point Cloud GAN.(arxiv 2018)

  • Learning representations and generative models for 3D point clouds.(ICML 2018)

  • Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling.(NIPS 2016)

Reconstruction

  • Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction.(AAAI 2018)

  • AtlasNet: A papiermache approach to learning 3D surface generation. (CVPR2017)

  • A point set generation network for 3D object reconstruction from a single image.(CVPR2017)

  • Learning efficient point cloud generation for dense 3D object reconstruction.(AAAI 2017)

Segmentation

Detection

  • Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction.(CVPR 2019)

  • MVX-Net: Multimodal VoxelNet for 3D Object Detection.(ICRA 2019)

  • Frustum PointNets for 3D object detection from RGB-D data.(CVPR 2018)

Denoise

  • 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation.(ICASSP 2019)

Completion

  • Unpaired Point Cloud Completion on Real Scans using Adversarial Training.(arxiv 2019)

Other Application

  • PointNetLK: Robust & Efficient Point Cloud Registration using PointNet.(CVPR 2019)

  • The Perfect Match: 3D Point Cloud Matching with Smoothed Densities.(CVPR 2019)

  • Embodied Question Answering in Photorealistic Environments with Point Cloud Perception.(CVPR 2019)

  • SDRSAC: Semidefinite*Based Randomized Approach for Robust Point Cloud Registration without Correspondences.(CVPR 2019)

  • Weighted Point Cloud Augmentation for Neural Network Training Data Class*Imblance.(ISRPS 2019)

  • Supervised Fitting of Geometric Primitives to 3D Point Clouds.(CVPR 2019 oral)

  • Revealing Scenes by Inverting Structure from Motion Reconstructions.(CVPR 2019)

  • DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds.(CVPR 2019 oral)(Unsupervised Learning)

  • USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds.(arxiv 2019)

  • PPF-FoldNet: Unsupervised learning of rotation invariant 3D local descriptors(ECCV 2018)