├── 3D_Point_Cloud_Paper.md └── README.md /3D_Point_Cloud_Paper.md: -------------------------------------------------------------------------------- 1 | # Point Cloud PaperList 2 | 3 | ## 目录 4 | 5 | * [Point-based networks](#Point-based-networks) 6 | * [Sample](#Sample) 7 | * [Generation](#Generation) 8 | * [Segmentation](#Segmentation) 9 | * [Detection](#Detection) 10 | * [Consolidation](#Consolidation) 11 | * [Deformation](#Deformation) 12 | * [Completion](#Completion) 13 | * [Denoise](#Denoise) 14 | 15 | ## Point-based networks 16 | 17 | ### pointnets 18 | 19 | * DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds.(arxiv 2019) 20 | 21 | * MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds.(arxiv 2019) 22 | 23 | * Discrete Rotation Equivariance for Point Cloud Recognition.(ICRA 2019) 24 | 25 | * Generalizing discrete convolutions for unstructured point clouds.(arxiv 2019) 26 | 27 | * Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions.(2019 Technical report) 28 | 29 | * 3D Local Features for Direct Pairwise Registration.(CVPR 2019) 30 | 31 | * Dynamic graph cnn for learning on point clouds.(arxiv 2018) 32 | 33 | * Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling(CVPR 2018) 34 | 35 | * Pointwise convolutional neural networks.(CVPR 2018) 36 | 37 | * PointCNN.(NIPS 2018) 38 | 39 | * PointSIFT: A SIFT-like network module for 3D point cloud semantic segmentation.(arxiv 2018) 40 | 41 | * Multiresolution tree networks for 3D point cloud processing.(ECCV 2018) 42 | 43 | * Fully-convolutional point networks for large-scale point clouds.(ECCV 2018) 44 | 45 | * PointNet: Deep learning on point sets for 3D classification and segmentation.(CVPR 2017) 46 | 47 | * PointNet++: Deep hierarchical feature learning on point sets in a metric space.(NIPS 2017) 48 | 49 | ### point cloud compression and representation 50 | 51 | * Point2Sequence: Learning the shape representation of 3D point clouds with an attention-based sequence to sequence network.（ACCV 2019) 52 | 53 | * Adaptive OCNN: A patch-based deep representation of 3D shapes(TOG 2018) 54 | 55 | * Escape from cells: deep KdNetworks for the recognition of 3D point cloud models.(ICCV 2017) 56 | 57 | * OctNet: Learning deep 3D representations at high resolutions.(CVPR 2017) 58 | 59 | ### volumetric methods 60 | 61 | * Shape completion using 3D*Encoder*Predictor CNNs and shape synthesis.(CVPR 2017) 62 | 63 | * OctNet: Learning deep 3D representations at high resolutions.(CVPR 2017) 64 | 65 | * Voxnet: A 3D convolutional neural network for real*time object recognition.(IROS 2015) 66 | 67 | * 3D ShapeNets: A deep representation for volumetric shapes.(CVPR 2015) 68 | 69 | ### geometric deep learning 70 | 71 | * Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs.(CVPR 2017) 72 | 73 | * Geodesic convolutional neural networks on Riemannian manifolds.(ICCV 2015) 74 | 75 | * Spectral networks and locally connected networks on graphs.(ICLR 2014) 76 | 77 | ## Sample 78 | 79 | * Learning to Sample.(CVPR 2019) 80 | 81 | * Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling.(CVPR 2019) 82 | 83 | * Ecnet: an edge-aware point set consolidation network.(ECCV 2018) 84 | 85 | * Data-driven upsampling of point clouds.(arxiv 2018) 86 | 87 | * Pointgrow: Autoregressively learned point cloud generation with self-attention.(arxiv 2018) 88 | 89 | * PU-Net: Point Cloud Upsampling Network.(CVPR 2018) 90 | 91 | * Deep points consolidation.(TOG 2015) 92 | 93 | * Edge-aware point set resampling.(TOG 2013) 94 | 95 | ## Generation 96 | 97 | ### Auto-Encoder method 98 | 99 | * Revealing Scenes by Inverting Structure from Motion Reconstructions.(CVPR 2019) 100 | 101 | * FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation.(CVPR 2018) 102 | 103 | ### Adversarial method 104 | 105 | * Point Cloud GAN.(arxiv 2018) 106 | 107 | * Learning representations and generative models for 3D point clouds.(ICML 2018) 108 | 109 | * Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling.(NIPS 2016) 110 | 111 | ### Reconstruction 112 | 113 | * Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction.(AAAI 2018) 114 | 115 | * AtlasNet: A papiermache approach to learning 3D surface generation. (CVPR2017) 116 | 117 | * A point set generation network for 3D object reconstruction from a single image.(CVPR2017) 118 | 119 | * Learning efficient point cloud generation for dense 3D object reconstruction.(AAAI 2017) 120 | 121 | ## Segmentation 122 | 123 | * Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning.(CVPR 2019) 124 | 125 | * JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with 126 | Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields(CVPR 2019) 127 | 128 | * 3D-BEVIS: Birds-Eye-View Instance Segmentation.(2019 technical Report) 129 | 130 | * [SGPN: Similarity group proposal network for 3D point cloud instance segmentation.](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SGPN_Similarity_Group_CVPR_2018_paper.pdf) (CVPR 2018) [Code](https://github.com/laughtervv/SGPN) 131 | 132 | ## Detection 133 | 134 | * Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction.(CVPR 2019) 135 | 136 | * MVX-Net: Multimodal VoxelNet for 3D Object Detection.(ICRA 2019) 137 | 138 | * Frustum PointNets for 3D object detection from RGB-D data.(CVPR 2018) 139 | 140 | ## Denoise 141 | 142 | * 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation.(ICASSP 2019) 143 | 144 | ## Completion 145 | 146 | * Unpaired Point Cloud Completion on Real Scans using Adversarial Training.(arxiv 2019) 147 | 148 | ## Other Application 149 | 150 | * PointNetLK: Robust & Efficient Point Cloud Registration using PointNet.(CVPR 2019) 151 | 152 | * The Perfect Match: 3D Point Cloud Matching with Smoothed Densities.(CVPR 2019) 153 | 154 | * Embodied Question Answering in Photorealistic Environments with Point Cloud Perception.(CVPR 2019) 155 | 156 | * SDRSAC: Semidefinite*Based Randomized Approach for Robust Point Cloud Registration without Correspondences.(CVPR 2019) 157 | 158 | * Weighted Point Cloud Augmentation for Neural Network Training Data Class*Imblance.(ISRPS 2019) 159 | 160 | * Supervised Fitting of Geometric Primitives to 3D Point Clouds.(CVPR 2019 oral) 161 | 162 | * Revealing Scenes by Inverting Structure from Motion Reconstructions.(CVPR 2019) 163 | 164 | * DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds.(CVPR 2019 oral)(Unsupervised Learning) 165 | 166 | * USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds.(arxiv 2019) 167 | 168 | * PPF-FoldNet: Unsupervised learning of rotation invariant 3D local descriptors(ECCV 2018) 169 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 3D-Deep-Learning-Paper-List 2 | 3 | * [Point-based networks](#Point-based-networks) 4 | * [Geometric Deep Learning](#Geometric-Deep-Learning) 5 | * [Sample](#Sample) 6 | * [Generation](#Generation) 7 | * [Segmentation](#Segmentation) 8 | * [Detection](#Detection) 9 | * [Consolidation](#Consolidation) 10 | * [Deformation](#Deformation) 11 | * [Completion](#Completion) 12 | * [Denoise](#Denoise) 13 | 14 | 15 | ## Point-based networks 16 | 17 | ### pointnets 18 | 19 | * DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds.(arxiv 2019) 20 | 21 | * MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds.(arxiv 2019) 22 | 23 | * Discrete Rotation Equivariance for Point Cloud Recognition.(ICRA 2019) 24 | 25 | * Generalizing discrete convolutions for unstructured point clouds.(arxiv 2019) 26 | 27 | * Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions.(2019 Technical report) 28 | 29 | * 3D Local Features for Direct Pairwise Registration.(CVPR 2019) 30 | 31 | * Dynamic graph cnn for learning on point clouds.(arxiv 2018) 32 | 33 | * Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling(CVPR 2018) 34 | 35 | * Pointwise convolutional neural networks.(CVPR 2018) 36 | 37 | * PointCNN.(NIPS 2018) 38 | 39 | * PointSIFT: A SIFT-like network module for 3D point cloud semantic segmentation.(arxiv 2018) 40 | 41 | * Multiresolution tree networks for 3D point cloud processing.(ECCV 2018) 42 | 43 | * Fully-convolutional point networks for large-scale point clouds.(ECCV 2018) 44 | 45 | * PointNet: Deep learning on point sets for 3D classification and segmentation.(CVPR 2017) 46 | 47 | * PointNet++: Deep hierarchical feature learning on point sets in a metric space.(NIPS 2017) 48 | 49 | ### point cloud compression and representation 50 | 51 | * Point2Sequence: Learning the shape representation of 3D point clouds with an attention-based sequence to sequence network.（AAAI 2019) 52 | 53 | * Adaptive OCNN: A patch-based deep representation of 3D shapes(TOG 2018) 54 | 55 | * Escape from cells: deep KdNetworks for the recognition of 3D point cloud models.(ICCV 2017) 56 | 57 | * OctNet: Learning deep 3D representations at high resolutions.(CVPR 2017) 58 | 59 | ### volumetric methods 60 | 61 | * Shape completion using 3D*Encoder*Predictor CNNs and shape synthesis.(CVPR 2017) 62 | 63 | * OctNet: Learning deep 3D representations at high resolutions.(CVPR 2017) 64 | 65 | * Voxnet: A 3D convolutional neural network for real*time object recognition.(IROS 2015) 66 | 67 | * 3D ShapeNets: A deep representation for volumetric shapes.(CVPR 2015) 68 | 69 | ## Geometric Deep Learning 70 | 71 | * Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs.(CVPR 2017) 72 | 73 | * Geodesic convolutional neural networks on Riemannian manifolds.(ICCV 2015) 74 | 75 | * Spectral networks and locally connected networks on graphs.(ICLR 2014) 76 | 77 | ## Sample 78 | 79 | * Learning to Sample.(CVPR 2019) 80 | 81 | * Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling.(CVPR 2019) 82 | 83 | * Ecnet: an edge-aware point set consolidation network.(ECCV 2018) 84 | 85 | * Data-driven upsampling of point clouds.(arxiv 2018) 86 | 87 | * Pointgrow: Autoregressively learned point cloud generation with self-attention.(arxiv 2018) 88 | 89 | * PU-Net: Point Cloud Upsampling Network.(CVPR 2018) 90 | 91 | * Deep points consolidation.(TOG 2015) 92 | 93 | * Edge-aware point set resampling.(TOG 2013) 94 | 95 | ## Generation and Reconstruction 96 | 97 | ### Auto-Encoder method 98 | 99 | * Revealing Scenes by Inverting Structure from Motion Reconstructions.(CVPR 2019) 100 | 101 | * FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation.(CVPR 2018) 102 | 103 | * Learning representations and generative models for 3D point clouds.(ICML 2018) 104 | 105 | * [A point set generation network for 3D object reconstruction from a single image.](https://arxiv.org/abs/1612.00603)(CVPR2017) 106 | 107 | ### Adversarial method 108 | 109 | * [Point Cloud GAN.](https://openreview.net/pdf?id=ByxAcjCqt7)(ICLR 2019) 110 | 111 | * [Learning Localized Generative Models for 3D Point Clouds via Graph Convolution.](https://openreview.net/pdf?id=SJeXSo09FQ)(ICLR 2019) 112 | 113 | * Learning representations and generative models for 3D point clouds.(ICML 2018) 114 | 115 | * Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling.(NIPS 2016) 116 | 117 | ### Other methods 118 | 119 | * Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction.(AAAI 2018) 120 | 121 | * AtlasNet: A papiermache approach to learning 3D surface generation. (CVPR2017) 122 | 123 | ## Segmentation 124 | 125 | * Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning.(CVPR 2019) 126 | 127 | * JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with 128 | Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields(CVPR 2019) 129 | 130 | * 3D-BEVIS: Birds-Eye-View Instance Segmentation.(2019 technical Report) 131 | 132 | * [SGPN: Similarity group proposal network for 3D point cloud instance segmentation.](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SGPN_Similarity_Group_CVPR_2018_paper.pdf) (CVPR 2018) [Code](https://github.com/laughtervv/SGPN) 133 | 134 | ## Detection 135 | 136 | * Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction.(CVPR 2019) 137 | 138 | * MVX-Net: Multimodal VoxelNet for 3D Object Detection.(ICRA 2019) 139 | 140 | * Frustum PointNets for 3D object detection from RGB-D data.(CVPR 2018) 141 | 142 | ## Denoise 143 | 144 | * 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation.(ICASSP 2019) 145 | 146 | ## Completion 147 | 148 | * Unpaired Point Cloud Completion on Real Scans using Adversarial Training.(arxiv 2019) 149 | 150 | ## Other Application 151 | 152 | * PointNetLK: Robust & Efficient Point Cloud Registration using PointNet.(CVPR 2019) 153 | 154 | * The Perfect Match: 3D Point Cloud Matching with Smoothed Densities.(CVPR 2019) 155 | 156 | * Embodied Question Answering in Photorealistic Environments with Point Cloud Perception.(CVPR 2019) 157 | 158 | * SDRSAC: Semidefinite*Based Randomized Approach for Robust Point Cloud Registration without Correspondences.(CVPR 2019) 159 | 160 | * Weighted Point Cloud Augmentation for Neural Network Training Data Class*Imblance.(ISRPS 2019) 161 | 162 | * Supervised Fitting of Geometric Primitives to 3D Point Clouds.(CVPR 2019 oral) 163 | 164 | * Revealing Scenes by Inverting Structure from Motion Reconstructions.(CVPR 2019) 165 | 166 | * DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds.(CVPR 2019 oral)(Unsupervised Learning) 167 | 168 | * USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds.(arxiv 2019) 169 | 170 | * PPF-FoldNet: Unsupervised learning of rotation invariant 3D local descriptors(ECCV 2018) 171 | --------------------------------------------------------------------------------