/awesome-point-cloud-analysis

A list of papers and datasets about point cloud analysis (processing)

awesome-point-cloud-analysis Awesome

for anyone who wants to do research about 3D point cloud.

If you find the awesome paper/code/dataset or have some suggestions, please contact hualin.vvv@gmail.com. Thanks for your valuable contribution to the research community πŸ˜ƒ

For more recent papers, please visit awesome-point-cloud-analysis-2020

- Recent papers (from 2017)

Keywords

dat.: dataset   |   cls.: classification   |   rel.: retrieval   |   seg.: segmentation
det.: detection   |   tra.: tracking   |   pos.: pose   |   dep.: depth
reg.: registration   |   rec.: reconstruction   |   aut.: autonomous driving
oth.: other, including normal-related, correspondence, mapping, matching, alignment, compression, generative model...

Statistics: πŸ”₯ code is available & stars >= 100  |  ⭐ citation >= 50


2017

  • [CVPR] PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. [tensorflow][pytorch] [cls. seg. det.] πŸ”₯ ⭐
  • [CVPR] Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs. [cls.] ⭐
  • [CVPR] SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. [torch] [seg. oth.] ⭐
  • [CVPR] ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. [project][git] [dat. cls. rel. seg. oth.] πŸ”₯ ⭐
  • [CVPR] Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity. [oth.]
  • [CVPR] Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures. [code] [oth.]
  • [CVPR] Discriminative Optimization: Theory and Applications to Point Cloud Registration. [reg.]
  • [CVPR] 3D Point Cloud Registration for Localization using a Deep Neural Network Auto-Encoder. [git] [reg.]
  • [CVPR] Multi-View 3D Object Detection Network for Autonomous Driving. [tensorflow] [det. aut.] πŸ”₯ ⭐
  • [CVPR] 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions. [code] [dat. pos. reg. rec. oth.] πŸ”₯ ⭐
  • [CVPR] OctNet: Learning Deep 3D Representations at High Resolutions. [torch] [cls. seg. oth.] πŸ”₯ ⭐
  • [ICCV] Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models. [pytorch] [cls. rel. seg.] ⭐
  • [ICCV] 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds. [code] [seg.]
  • [ICCV] Colored Point Cloud Registration Revisited. [reg.]
  • [ICCV] PolyFit: Polygonal Surface Reconstruction from Point Clouds. [code] [rec.] πŸ”₯
  • [ICCV] From Point Clouds to Mesh using Regression. [rec.]
  • [ICCV] 3D Graph Neural Networks for RGBD Semantic Segmentation. [pytorch] [seg.]
  • [NeurIPS] PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. [tensorflow][pytorch] [cls. seg.] πŸ”₯ ⭐
  • [NeurIPS] Deep Sets. [pytorch] [cls.] ⭐
  • [ICRA] Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks. [code] [det. aut.] ⭐
  • [ICRA] Fast segmentation of 3D point clouds: A paradigm on LiDAR data for autonomous vehicle applications. [code] [seg. aut.]
  • [ICRA] SegMatch: Segment based place recognition in 3D point clouds. [seg. oth.]
  • [ICRA] Using 2 point+normal sets for fast registration of point clouds with small overlap. [reg.]
  • [IROS] Car detection for autonomous vehicle: LIDAR and vision fusion approach through deep learning framework. [det. aut.]
  • [IROS] 3D object classification with point convolution network. [cls.]
  • [IROS] 3D fully convolutional network for vehicle detection in point cloud. [tensorflow] [det. aut.] πŸ”₯ ⭐
  • [IROS] Deep learning of directional truncated signed distance function for robust 3D object recognition. [det. pos.]
  • [IROS] Analyzing the quality of matched 3D point clouds of objects. [oth.]
  • [3DV] SEGCloud: Semantic Segmentation of 3D Point Clouds. [project] [seg. aut.] ⭐
  • [TPAMI] Structure-aware Data Consolidation. [oth.]

2018

  • [CVPR] SPLATNet: Sparse Lattice Networks for Point Cloud Processing. [caffe] [seg.] πŸ”₯
  • [CVPR] Attentional ShapeContextNet for Point Cloud Recognition. [cls. seg.]
  • [CVPR] Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling. [code] [cls. seg.]
  • [CVPR] FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. [code] [cls.]
  • [CVPR] Pointwise Convolutional Neural Networks. [tensorflow] [cls. seg.]
  • [CVPR] PU-Net: Point Cloud Upsampling Network. [tensorflow] [rec. oth.] πŸ”₯
  • [CVPR] SO-Net: Self-Organizing Network for Point Cloud Analysis. [pytorch] [cls. seg.] πŸ”₯ ⭐
  • [CVPR] Recurrent Slice Networks for 3D Segmentation of Point Clouds. [pytorch] [seg.]
  • [CVPR] 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks. [pytorch] [seg.] πŸ”₯
  • [CVPR] Deep Parametric Continuous Convolutional Neural Networks. [seg. aut.]
  • [CVPR] PIXOR: Real-time 3D Object Detection from Point Clouds. [pytorch] [det. aut.]
  • [CVPR] SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation. [tensorflow] [seg.] πŸ”₯
  • [CVPR] Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs. [pytorch] [seg.] πŸ”₯
  • [CVPR] VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection. [tensorflow] [det. aut.] πŸ”₯ ⭐
  • [CVPR] Reflection Removal for Large-Scale 3D Point Clouds. [oth.]
  • [CVPR] Hand PointNet: 3D Hand Pose Estimation using Point Sets. [pytorch] [pos.]
  • [CVPR] PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition. [tensorflow] [rel.] πŸ”₯
  • [CVPR] A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation. [cls.]
  • [CVPR] Density Adaptive Point Set Registration. [code] [reg.]
  • [CVPR] A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds. [seg.]
  • [CVPR] Inverse Composition Discriminative Optimization for Point Cloud Registration. [reg.]
  • [CVPR] CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles. [tra. det. rec.]
  • [CVPR] PPFNet: Global Context Aware Local Features for Robust 3D Point Matching. [oth.]
  • [CVPR] PointGrid: A Deep Network for 3D Shape Understanding. [tensorflow] [cls. seg.]
  • [CVPR] PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation. [code] [det. aut.]
  • [CVPR] Frustum PointNets for 3D Object Detection from RGB-D Data. [tensorflow] [det. aut.] πŸ”₯ ⭐
  • [CVPR] Tangent Convolutions for Dense Prediction in 3D. [tensorflow] [seg. aut.]
  • [ECCV] Multiresolution Tree Networks for 3D Point Cloud Processing. [pytorch] [cls.]
  • [ECCV] EC-Net: an Edge-aware Point set Consolidation Network. [tensorflow] [oth.]
  • [ECCV] 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation. [seg.]
  • [ECCV] Learning and Matching Multi-View Descriptors for Registration of Point Clouds. [reg.]
  • [ECCV] 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration. [tensorflow] [reg.]
  • [ECCV] Local Spectral Graph Convolution for Point Set Feature Learning. [tensorflow] [cls. seg.]
  • [ECCV] SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters. [tensorflow] [cls. seg.]
  • [ECCV] Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search. [reg.]
  • [ECCV] Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields. [rec.]
  • [ECCV] Fully-Convolutional Point Networks for Large-Scale Point Clouds. [tensorflow] [seg. oth.]
  • [ECCV] Deep Continuous Fusion for Multi-Sensor 3D Object Detection. [det.]
  • [ECCV] HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration. [reg.]
  • [ECCV] Point-to-Point Regression PointNet for 3D Hand Pose Estimation. [pos.]
  • [ECCV] PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors. [oth.]
  • [ECCVW] 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues. [cls. seg.]
  • [ECCVW] YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud. [det. aut.]
  • [AAAI] Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction. [tensorflow] [rec.] πŸ”₯
  • [AAAI] Adaptive Graph Convolutional Neural Networks. [cls.]
  • [NeurIPS] Unsupervised Learning of Shape and Pose with Differentiable Point Clouds. [tensorflow] [pos.]
  • [NeurIPS] PointCNN: Convolution On X-Transformed Points. [tensorflow][pytorch] [cls. seg.] πŸ”₯
  • [ICML] Learning Representations and Generative Models for 3D Point Clouds. [code] [oth.] πŸ”₯
  • [TOG] Point Convolutional Neural Networks by Extension Operators. [tensorflow] [cls. seg.]
  • [SIGGRAPH] P2P-NET: Bidirectional Point Displacement Net for Shape Transform. [tensorflow] [oth.]
  • [SIGGRAPH Asia] Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds. [tensorflow] [cls. seg. oth.]
  • [SIGGRAPH] Learning local shape descriptors from part correspondences with multi-view convolutional networks. [project] [seg. oth.]
  • [MM] PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition. [cls. rel.]
  • [MM] RGCNN: Regularized Graph CNN for Point Cloud Segmentation. [tensorflow] [seg.]
  • [MM] Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction. [oth.]
  • [ICRA] End-to-end Learning of Multi-sensor 3D Tracking by Detection. [det. tra. aut.]
  • [ICRA] Multi-View 3D Entangled Forest for Semantic Segmentation and Mapping. [seg. oth.]
  • [ICRA] SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud. [tensorflow] [seg. aut.]
  • [ICRA] Robust Real-Time 3D Person Detection for Indoor and Outdoor Applications. [det.]
  • [ICRA] High-Precision Depth Estimation with the 3D LiDAR and Stereo Fusion. [dep. aut.]
  • [ICRA] Sampled-Point Network for Classification of Deformed Building Element Point Clouds. [cls.]
  • [ICRA] Gemsketch: Interactive Image-Guided Geometry Extraction from Point Clouds. [oth.]
  • [ICRA] Signature of Topologically Persistent Points for 3D Point Cloud Description. [oth.]
  • [ICRA] A General Pipeline for 3D Detection of Vehicles. [det. aut.]
  • [ICRA] Robust and Fast 3D Scan Alignment Using Mutual Information. [oth.]
  • [ICRA] Delight: An Efficient Descriptor for Global Localisation Using LiDAR Intensities. [oth.]
  • [ICRA] Surface-Based Exploration for Autonomous 3D Modeling. [oth. aut.]
  • [ICRA] Deep Lidar CNN to Understand the Dynamics of Moving Vehicles. [oth. aut.]
  • [ICRA] Dex-Net 3.0: Computing Robust Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning. [oth.]
  • [ICRA] Real-Time Object Tracking in Sparse Point Clouds Based on 3D Interpolation. [tra.]
  • [ICRA] Robust Generalized Point Cloud Registration Using Hybrid Mixture Model. [reg.]
  • [ICRA] A General Framework for Flexible Multi-Cue Photometric Point Cloud Registration. [reg.]
  • [ICRA] Efficient Continuous-Time SLAM for 3D Lidar-Based Online Mapping. [oth.]
  • [ICRA] Direct Visual SLAM Using Sparse Depth for Camera-LiDAR System. [oth.]
  • [ICRA] Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data. [cls.]
  • [ICRA] Asynchronous Multi-Sensor Fusion for 3D Mapping and Localization. [oth.]
  • [ICRA] Complex Urban LiDAR Data Set. [video] [dat. oth.]
  • [IROS] CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks.[tensorflow] [oth. aut.]
  • [IROS] Dynamic Scaling Factors of Covariances for Accurate 3D Normal Distributions Transform Registration. [reg.]
  • [IROS] A 3D Laparoscopic Imaging System Based on Stereo-Photogrammetry with Random Patterns. [rec. oth.]
  • [IROS] Robust Generalized Point Cloud Registration with Expectation Maximization Considering Anisotropic Positional Uncertainties. [reg.]
  • [IROS] Octree map based on sparse point cloud and heuristic probability distribution for labeled images. [oth. aut.]
  • [IROS] PoseMap: Lifelong, Multi-Environment 3D LiDAR Localization. [oth.]
  • [IROS] Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map. [oth.]
  • [IROS] LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain.[code] [pos. oth.] πŸ”₯
  • [IROS] Classification of Hanging Garments Using Learned Features Extracted from 3D Point Clouds. [cls.]
  • [IROS] Stereo Camera Localization in 3D LiDAR Maps. [pos. oth.]
  • [IROS] Joint 3D Proposal Generation and Object Detection from View Aggregation. [det.] ⭐
  • [IROS] Joint Point Cloud and Image Based Localization for Efficient Inspection in Mixed Reality. [oth.]
  • [IROS] Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding. [det. oth.]
  • [IROS] NDVI Point Cloud Generator Tool Using Low-Cost RGB-D Sensor. [code][oth.]
  • [IROS] A 3D Convolutional Neural Network Towards Real-Time Amodal 3D Object Detection. [det. pos.]
  • [IROS] Extracting Phenotypic Characteristics of Corn Crops Through the Use of Reconstructed 3D Models. [seg. rec.]
  • [IROS] PCAOT: A Manhattan Point Cloud Registration Method Towards Large Rotation and Small Overlap. [reg.]
  • [IROS] [Tensorflow]3DmFV: Point Cloud Classification and segmentation for unstructured 3D point clouds. [cls. ]
  • [IROS] Seeing the Wood for the Trees: Reliable Localization in Urban and Natural Environments. [oth. ]
  • [SENSORS] SECOND: Sparsely Embedded Convolutional Detection. [pytorch] [det. aut.] πŸ”₯
  • [ACCV] Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds). [tensorflow] [seg.]
  • [3DV] PCN: Point Completion Network. [tensorflow] [reg. oth. aut.] πŸ”₯
  • [ICASSP] A Graph-CNN for 3D Point Cloud Classification. [tensorflow] [cls.] πŸ”₯
  • [ITSC] BirdNet: a 3D Object Detection Framework from LiDAR information. [det. aut.]
  • [arXiv] PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation. [tensorflow] [seg.] πŸ”₯
  • [arXiv] Spherical Convolutional Neural Network for 3D Point Clouds. [cls.]
  • [arXiv] Adversarial Autoencoders for Generating 3D Point Clouds. [oth.]
  • [arXiv] Iterative Transformer Network for 3D Point Cloud. [cls. seg. pos.]
  • [arXiv] Topology-Aware Surface Reconstruction for Point Clouds. [rec.]
  • [arXiv] Inferring Point Clouds from Single Monocular Images by Depth Intermediation. [oth.]
  • [arXiv] Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions. [cls.]
  • [arXiv] IPOD: Intensive Point-based Object Detector for Point Cloud. [det.]
  • [arXiv] Feature Preserving and Uniformity-controllable Point Cloud Simplification on Graph. [oth.]
  • [arXiv] POINTCLEANNET: Learning to Denoise and Remove Outliers from Dense Point Clouds. [pytorch] [oth.]
  • [arXiv] Complex-YOLO: Real-time 3D Object Detection on Point Clouds. [pytorch] [det. aut.] πŸ”₯
  • [arxiv] RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement. [tensorflow] [det. aut.]
  • [arXiv] Multi-column Point-CNN for Sketch Segmentation. [seg.]
  • [arXiv] PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention. [project] [oth.]
  • [arXiv] Point Cloud GAN. [pytorch] [oth.]

2019

  • [CVPR] Relation-Shape Convolutional Neural Network for Point Cloud Analysis. [pytorch] [cls. seg. oth.] πŸ”₯
  • [CVPR] Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition. [cls. seg.]
  • [CVPR] DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds. [code] [reg.]
  • [CVPR] Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving. [code] [det. dep. aut.]
  • [CVPR] PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud. [pytorch] [det. aut.] πŸ”₯
  • [CVPR] Generating 3D Adversarial Point Clouds. [code] [oth.]
  • [CVPR] Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling. [cls. seg.]
  • [CVPR] A-CNN: Annularly Convolutional Neural Networks on Point Clouds. [tensorflow][cls. seg.]
  • [CVPR] PointConv: Deep Convolutional Networks on 3D Point Clouds. [tensorflow] [cls. seg.] πŸ”₯
  • [CVPR] Path-Invariant Map Networks. [tensorflow] [seg. oth.]
  • [CVPR] PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. [code] [dat. seg.]
  • [CVPR] GeoNet: Deep Geodesic Networks for Point Cloud Analysis. [cls. rec. oth.]
  • [CVPR] Associatively Segmenting Instances and Semantics in Point Clouds. [tensorflow] [seg.] πŸ”₯
  • [CVPR] Supervised Fitting of Geometric Primitives to 3D Point Clouds. [tensorflow] [oth.]
  • [CVPR] Octree guided CNN with Spherical Kernels for 3D Point Clouds. [extension] [code] [cls. seg.]
  • [CVPR] PointNetLK: Point Cloud Registration using PointNet. [pytorch] [reg.]
  • [CVPR] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields. [pytorch] [seg.]
  • [CVPR] Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning. [seg.]
  • [CVPR] PointPillars: Fast Encoders for Object Detection from Point Clouds. [pytorch] [det.] πŸ”₯
  • [CVPR] Patch-based Progressive 3D Point Set Upsampling. [tensorflow] [oth.]
  • [CVPR] PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval. [code] [rel.]
  • [CVPR] PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation. [pytorch] [dat. seg.]
  • [CVPR] PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds. [code] [det. dat. oth.]
  • [CVPR] SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences. [matlab] [reg.]
  • [CVPR] Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image. [rec. oth.]
  • [CVPR] Embodied Question Answering in Photorealistic Environments with Point Cloud Perception. [oth.]
  • [CVPR] 3D Point-Capsule Networks. [pytorch] [cls. rec. oth.]
  • [CVPR] 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. [pytorch] [seg.] πŸ”₯
  • [CVPR] The Perfect Match: 3D Point Cloud Matching with Smoothed Densities. [tensorflow] [oth.]
  • [CVPR] FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization. [code] [reg.]
  • [CVPR] FlowNet3D: Learning Scene Flow in 3D Point Clouds. [oth.]
  • [CVPR] Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN. [cls. det.]
  • [CVPR] ClusterNet: Deep Hierarchical Cluster Network with Rigorously Rotation-Invariant Representation for Point Cloud Analysis. [cls.]
  • [CVPR] PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing. [pytorch] [cls. seg.]
  • [CVPR] RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion. [code] [oth.]
  • [CVPR] PointNetLK: Robust & Efficient Point Cloud Registration using PointNet. [pytorch] [reg.]
  • [CVPR] Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes. [code] [rec.]
  • [CVPR] Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks. [tensorflow] [oth.]
  • [CVPR] GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud. [seg.]
  • [CVPR] Graph Attention Convolution for Point Cloud Semantic Segmentation. [seg.]
  • [CVPR] Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer. [pos.]
  • [CVPR] LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving. [det. aut.]
  • [CVPR] LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks. [project] [cls. seg.]
  • [CVPR] Structural Relational Reasoning of Point Clouds. [cls. seg.]
  • [CVPR] 3DN: 3D Deformation Network. [tensorflow] [rec. oth.]
  • [CVPR] Privacy Preserving Image-Based Localization. [pos. oth.]
  • [CVPR] Argoverse: 3D Tracking and Forecasting With Rich Maps.[tra. aut.]
  • [CVPR] Leveraging Shape Completion for 3D Siamese Tracking. [pytorch] [tra. ]
  • [CVPRW] Attentional PointNet for 3D-Object Detection in Point Clouds. [pytorch] [cls. det. aut.]
  • [CVPR] 3D Local Features for Direct Pairwise Registration. [reg.]
  • [CVPR] Learning to Sample. [tensorflow] [cls. rec.]
  • [CVPR] Revealing Scenes by Inverting Structure from Motion Reconstructions. [code] [rec.]
  • [CVPR] DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image. [pytorch] [dep.]
  • [CVPR] HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds. [pytorch] [oth.]
  • [ICCV] Deep Hough Voting for 3D Object Detection in Point Clouds. [pytorch] [tensorflow] [det.] πŸ”₯
  • [ICCV] DeepGCNs: Can GCNs Go as Deep as CNNs? [tensorflow] [pytorch] [seg.] πŸ”₯
  • [ICCV] PU-GAN: a Point Cloud Upsampling Adversarial Network. [tensorflow] [oth.]
  • [ICCV] 3D Point Cloud Learning for Large-scale Environment Analysis and Place Recognition. [rel. oth.]
  • [ICCV] PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows. [pytorch] [oth.]
  • [ICCV] Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction. [oth.]
  • [ICCV] SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning. [code] [pos.]
  • [ICCV] DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense. [oth.]
  • [ICCV] Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data. [cls. dat.] [code] [dataset]
  • [ICCV] KPConv: Flexible and Deformable Convolution for Point Clouds. [tensorflow] [cls. seg.] πŸ”₯
  • [ICCV] ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics. [project] [seg.]
  • [ICCV] Point-Based Multi-View Stereo Network. [pytorch] [rec.]
  • [ICCV] DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing. [pytorch] [cls. seg. oth.]
  • [ICCV] DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration. [reg.]
  • [ICCV] 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions. [pytorch] [oth.]
  • [ICCV] Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. [seg.]
  • [ICCV] Learning an Effective Equivariant 3D Descriptor Without Supervision. [oth.]
  • [ICCV] Fully Convolutional Geometric Features. [pytorch] [reg.]
  • [ICCV] LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis. [oth. aut.]
  • [ICCV] Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning. [tensorflow] [oth.]
  • [ICCV] USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds. [pytorch] [oth.]
  • [ICCV] Interpolated Convolutional Networks for 3D Point Cloud Understanding. [cls. seg.]
  • [ICCV] PointCloud Saliency Maps. [code] [oth.]
  • [ICCV] STD: Sparse-to-Dense 3D Object Detector for Point Cloud. [det. oth.]
  • [ICCV] Accelerated Gravitational Point Set Alignment with Altered Physical Laws. [reg.]
  • [ICCV] Deep Closest Point: Learning Representations for Point Cloud Registration. [reg.]
  • [ICCV] Efficient Learning on Point Clouds with Basis Point Sets. [code] [cls. reg.]
  • [ICCV] PointAE: Point Auto-encoder for 3D Statistical Shape and Texture Modelling. [rec.]
  • [ICCV] Skeleton-Aware 3D Human Shape Reconstruction From Point Clouds. [rec.]
  • [ICCV] Dynamic Points Agglomeration for Hierarchical Point Sets Learning. [pytorch] [cls. seg.]
  • [ICCV] Unsupervised Multi-Task Feature Learning on Point Clouds. [cls. seg.]
  • [ICCV] VV-NET: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation. [tensorflow] [seg.]
  • [ICCV] GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion. [pytorch] [rec.]
  • [ICCV] MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences. [code] [cls. seg. oth.]
  • [ICCV] Fast Point R-CNN. [det. aut.]
  • [ICCV] Robust Variational Bayesian Point Set Registration. [reg.]
  • [ICCV] DiscoNet: Shapes Learning on Disconnected Manifolds for 3D Editing. [rec. oth.]
  • [ICCV] Learning an Effective Equivariant 3D Descriptor Without Supervision. [oth.]
  • [ICCV] 3D Instance Segmentation via Multi-Task Metric Learning. [code] [seg.]
  • [ICCV] 3D Face Modeling From Diverse Raw Scan Data. [rec.]
  • [ICCVW] Range Adaptation for 3D Object Detection in LiDAR. [det. aut.]
  • [NeurIPS] Self-Supervised Deep Learning on Point Clouds by Reconstructing Space. [cls. oth.]
  • [NeurIPS] Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. [tensorflow] [det. seg.]
  • [NeurIPS] Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations. [tensorflow] [seg.]
  • [NeurIPS] Point-Voxel CNN for Efficient 3D Deep Learning. [det. seg. aut.]
  • [NeurIPS] PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation. [code] [cls. oth.]
  • [ICLR] Learning Localized Generative Models for 3D Point Clouds via Graph Convolution. [oth.]
  • [ICMLW] LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving. [det. oth. aut.]
  • [AAAI] CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision. [code] [rec.]
  • [AAAI] Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network. [tensorflow] [cls. seg.]
  • [AAAI] Point Cloud Processing via Recurrent Set Encoding. [cls.]
  • [AAAI] PVRNet: Point-View Relation Neural Network for 3D Shape Recognition. [pytorch] [cls. rel.]
  • [AAAI] Hypergraph Neural Networks. [pytorch] [cls.]
  • [TOG] Dynamic Graph CNN for Learning on Point Clouds. [tensorflow][pytorch] [cls. seg.] πŸ”₯ ⭐
  • [TOG] LOGAN: Unpaired Shape Transform in Latent Overcomplete Space. [tensorflow] [oth.]
  • [SIGGRAPH Asia] RPM-Net: recurrent prediction of motion and parts from point cloud. [tensorflow] [seg.]
  • [SIGGRAPH Asia] StructureNet: Hierarchical Graph Networks for 3D Shape Generation. [seg. oth.]
  • [MM] MMJN: Multi-Modal Joint Networks for 3D Shape Recognition. [cls. rel.]
  • [MM] 3D Point Cloud Geometry Compression on Deep Learning. [oth.]
  • [MM] SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation. [tensorflow] [cls. seg.]
  • [MM] L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention. [cls. rel.]
  • [MM] Ground-Aware Point Cloud Semantic Segmentation for Autonomous Driving. [code] [seg. aut.]
  • [ICME] Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables. [cls. rel.]
  • [ICASSP] 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation. [code] [oth.]
  • [BMVC] Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects. [cls.]
  • [ICRA] Discrete Rotation Equivariance for Point Cloud Recognition. [pytorch] [cls.]
  • [ICRA] SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud. [tensorflow] [seg. aut.]
  • [ICRA] Detection and Tracking of Small Objects in Sparse 3D Laser Range Data. [det. tra. aut.]
  • [ICRA] Oriented Point Sampling for Plane Detection in Unorganized Point Clouds. [det. seg.]
  • [ICRA] Point Cloud Compression for 3D LiDAR Sensor Using Recurrent Neural Network with Residual Blocks. [pytorch] [oth.]
  • [ICRA] Focal Loss in 3D Object Detection. [code] [det. aut.]
  • [ICRA] PointNetGPD: Detecting Grasp Configurations from Point Sets. [pytorch] [det. seg.]
  • [ICRA] 2D3D-MatchNet: Learning to Match Keypoints across 2D Image and 3D Point Cloud. [oth.]
  • [ICRA] Speeding up Iterative Closest Point Using Stochastic Gradient Descent. [oth.]
  • [ICRA] Uncertainty Estimation for Projecting Lidar Points Onto Camera Images for Moving Platforms. [oth.]
  • [ICRA] SEG-VoxelNet for 3D Vehicle Detection from RGB and LiDAR Data. [det. aut.]
  • [ICRA] BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving. [project] [dat. det. tra. aut. oth.]
  • [ICRA] A Fast and Robust 3D Person Detector and Posture Estimator for Mobile Robotic Applications. [det.]
  • [ICRA] Robust low-overlap 3-D point cloud registration for outlier rejection. [matlab] [reg.]
  • [ICRA] Robust 3D Object Classification by Combining Point Pair Features and Graph Convolution. [cls. seg.]
  • [ICRA] Hierarchical Depthwise Graph Convolutional Neural Network for 3D Semantic Segmentation of Point Clouds. [seg.]
  • [ICRA] Robust Generalized Point Set Registration Using Inhomogeneous Hybrid Mixture Models Via Expectation. [reg.]
  • [ICRA] Dense 3D Visual Mapping via Semantic Simplification. [oth.]
  • [ICRA] MVX-Net: Multimodal VoxelNet for 3D Object Detection. [det. aut.]
  • [ICRA] CELLO-3D: Estimating the Covariance of ICP in the Real World. [reg.]
  • [IROS] EPN: Edge-Aware PointNet for Object Recognition from Multi-View 2.5D Point Clouds. [tensorflow] [cls. det.]
  • [IROS] SeqLPD: Sequence Matching Enhanced Loop-Closure Detection Based on Large-Scale Point Cloud Description for Self-Driving Vehicles. [oth.] [aut.]
  • [IROS] PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud. [seg. aut.]
  • [IV] End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving. [seg.] [aut.]
  • [Eurographics Workshop] Generalizing Discrete Convolutions for Unstructured Point Clouds. [pytorch] [cls. seg.]
  • [WACV] 3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds. [cls.]
  • [3DV] Rotation Invariant Convolutions for 3D Point Clouds Deep Learning. [project] [cls. seg.]
  • [3DV] Effective Rotation-invariant Point CNN with Spherical Harmonics kernels. [tensorflow] [cls. seg. oth.]
  • [TVCG] LassoNet: Deep Lasso-Selection of 3D Point Clouds. [project] [oth.]
  • [arXiv] Fast 3D Line Segment Detection From Unorganized Point Cloud. [det.]
  • [arXiv] Point-Cloud Saliency Maps. [tensorflow] [cls. oth.]
  • [arXiv] Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers. [code] [oth.]
  • [arxiv] Context Prediction for Unsupervised Deep Learning on Point Clouds. [cls. seg.]
  • [arXiv] Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks. [oth.]
  • [arXiv] NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler. [cls. oth.]
  • [arXiv] 3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation. [seg.]
  • [arXiv] Zero-shot Learning of 3D Point Cloud Objects. [code] [cls.]
  • [arXiv] Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud. [det. aut.]
  • [arXiv] Real-time Multiple People Hand Localization in 4D Point Clouds. [det. oth.]
  • [arXiv] Variational Graph Methods for Efficient Point Cloud Sparsification. [oth.]
  • [arXiv] Neural Style Transfer for Point Clouds. [oth.]
  • [arXiv] OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios. [pos. oth.]
  • [arXiv] FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds. [code] [det. aut.]
  • [arXiv] Unpaired Point Cloud Completion on Real Scans using Adversarial Training. [oth.]
  • [arXiv] MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds. [cls. seg.]
  • [arXiv] DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds. [cls. rel. oth.]
  • [arXiv] Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds. [pytorch] [det. tra. aut.] πŸ”₯
  • [arXiv] Graph-based Inpainting for 3D Dynamic Point Clouds. [oth.]
  • [arXiv] nuScenes: A multimodal dataset for autonomous driving. [link] [dat. det. tra. aut.]
  • [arXiv] 3D Backbone Network for 3D Object Detection. [code] [det. aut.]
  • [arXiv] Adversarial Autoencoders for Compact Representations of 3D Point Clouds. [pytorch] [rel. oth.]
  • [arXiv] Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features. [cls. seg.]
  • [arXiv] GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud. [tensorflow] [cls. seg.]
  • [arXiv] Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. [tensorflow] [det. seg.]
  • [arXiv] Differentiable Surface Splatting for Point-based Geometry Processing. [pytorch] [oth.]
  • [arXiv] Spatial Transformer for 3D Points. [seg.]
  • [arXiv] Point-Voxel CNN for Efficient 3D Deep Learning. [seg. det. aut.]
  • [arXiv] Neural Point-Based Graphics. [project] [oth.]
  • [arXiv] Point Cloud Super Resolution with Adversarial Residual Graph Networks. [oth.] [tensorflow]
  • [arXiv] Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes. [cls. rel.]
  • [arXiv] StarNet: Targeted Computation for Object Detection in Point Clouds. [tensorflow] [det.]
  • [arXiv] Efficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR. [tra.]
  • [arXiv] SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing. [tensorflow] [cls. seg.]
  • [arXiv] Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud. [det. aut.]
  • [arXiv] PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation. [cls. seg.]
  • [arXiv] PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing. [tensorflow] [tra. oth. aut.]
  • [arXiv] PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points. [tensorflow] [cls. seg.]
  • [arXiv] Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds. [oth.]
  • [arXiv] 3D-Rotation-Equivariant Quaternion Neural Networks. [cls. rec.]
  • [arXiv] Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules. [cls. rel. seg.]
  • [arXiv] Geometric Feedback Network for Point Cloud Classification. [cls.]
  • [arXiv] Relation Graph Network for 3D Object Detection in Point Clouds. [det.]
  • [arXiv] Deformable Filter Convolution for Point Cloud Reasoning. [seg. det. aut.]
  • [arXiv] PU-GCN: Point Cloud Upsampling via Graph Convolutional Network. [project] [oth.]
  • [arXiv] StructEdit: Learning Structural Shape Variations. [project] [rec.]
  • [arXiv] Grid-GCN for Fast and Scalable Point Cloud Learning. [seg. cls.]
  • [arXiv] PointPainting: Sequential Fusion for 3D Object Detection. [seg. det.]
  • [arXiv] Transductive Zero-Shot Learning for 3D Point Cloud Classification. [cls.]
  • [arXiv] Geometry Sharing Network for 3D Point Cloud Classification and Segmentation. [pytorch] [cls. seg.]
  • [arvix] Deep Learning for 3D Point Clouds: A Survey. [code] [cls. det. tra. seg.]
  • [arXiv] Spectral-GANs for High-Resolution 3D Point-cloud Generation. [rec. oth.]
  • [arXiv] Point Attention Network for Semantic Segmentation of 3D Point Clouds. [seg.]
  • [arXiv] PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation. [oth.]
  • [arXiv] 3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning Models. [cls. det.]

2020

  • [AAAI] Morphing and Sampling Network for Dense Point Cloud Completion. [pytorch] [oth.]
  • [AAAI] TANet: Robust 3D Object Detection from Point Clouds with Triple Attention. [code] [det. aut.]
  • [AAAI] Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling. [seg. cls.]
  • [AAAI] PRIN: Pointwise Rotation-Invariant Network. [seg. cls.]
  • [CVPR] Just Go with the Flow: Self-Supervised Scene Flow Estimation. [code][aut. oth.]
  • [CVPR] SGAS: Sequential Greedy Architecture Search. [code] [cls. oth.]
  • [CVPR] RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds. [tensorflow] [seg.]
  • [CVPR] Learning multiview 3D point cloud registration. [code] [reg.]
  • [CVPR] PF-Net: Point Fractal Network for 3D Point Cloud Completion. [pytorch] [oth.]
  • [CVPR] MLCVNet: Multi-Level Context VoteNet for 3D Object Detection. [code] [det.]
  • [CVPR] SampleNet: Differentiable Point Cloud Sampling. [code] [cls. reg. rec. oth.]
  • [CVPR] MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignment. [reg. oth.]
  • [CVPR] Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences. [code] [reg.]
  • [CVPR] Attentive Context Normalization for Robust Permutation-Equivariant Learning. [code] [cls.]
  • [CVPR] Implicit Functions in Feature Space for Shape Reconstruction and Completion. [code] [oth.]
  • [CVPR] PointAugment: an Auto-Augmentation Framework for Point Cloud Classification. [cls.]
  • [WACV] FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data. [seg. aut.]
  • [arXiv] ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes. [det.]
  • [ECCV] Quaternion Equivariant Capsule Networks for 3D Point Clouds. [cls.]
  • [ECCV] PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding. [cls. seg. det.]
  • [ECCV] DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares. [code] [oth.]
  • [ECCV] DPDist: Comparing Point Clouds Using Deep Point Cloud Distance. [code] [oth.]
  • [IROS] GndNet: Fast Ground Plane Estimation and Point Cloud Segmentation for Autonomous Vehicles. [code] [seg. aut.]
  • [ICLR] AdvectiveNet: An Eulerian-Lagrangian Fluidic Reservoir for Point Cloud Processing. [code][cls. seg.]

2021

  • [ICLR] PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences. [cls. seg.]
  • [CVPR] Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos. [code][cls. seg.]
  • [CVPR] PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds. [code][oth.]
  • [ICRA] FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection. [code][det. seg.]

- Datasets

  • [KITTI] The KITTI Vision Benchmark Suite. [det.]
  • [ModelNet] The Princeton ModelNet . [cls.]
  • [ShapeNet] A collaborative dataset between researchers at Princeton, Stanford and TTIC. [seg.]
  • [PartNet] The PartNet dataset provides fine grained part annotation of objects in ShapeNetCore. [seg.]
  • [PartNet] PartNet benchmark from Nanjing University and National University of Defense Technology. [seg.]
  • [S3DIS] The Stanford Large-Scale 3D Indoor Spaces Dataset. [seg.]
  • [ScanNet] Richly-annotated 3D Reconstructions of Indoor Scenes. [cls. seg.]
  • [Stanford 3D] The Stanford 3D Scanning Repository. [reg.]
  • [UWA Dataset] . [cls. seg. reg.]
  • [Princeton Shape Benchmark] The Princeton Shape Benchmark.
  • [SYDNEY URBAN OBJECTS DATASET] This dataset contains a variety of common urban road objects scanned with a Velodyne HDL-64E LIDAR, collected in the CBD of Sydney, Australia. There are 631 individual scans of objects across classes of vehicles, pedestrians, signs and trees. [cls. match.]
  • [ASL Datasets Repository(ETH)] This site is dedicated to provide datasets for the Robotics community with the aim to facilitate result evaluations and comparisons. [cls. match. reg. det]
  • [Large-Scale Point Cloud Classification Benchmark(ETH)] This benchmark closes the gap and provides a large labelled 3D point cloud data set of natural scenes with over 4 billion points in total. [cls.]
  • [Robotic 3D Scan Repository] The Canadian Planetary Emulation Terrain 3D Mapping Dataset is a collection of three-dimensional laser scans gathered at two unique planetary analogue rover test facilities in Canada.
  • [Radish] The Robotics Data Set Repository (Radish for short) provides a collection of standard robotics data sets.
  • [IQmulus & TerraMobilita Contest] The database contains 3D MLS data from a dense urban environment in Paris (France), composed of 300 million points. The acquisition was made in January 2013. [cls. seg. det.]
  • [Oakland 3-D Point Cloud Dataset] This repository contains labeled 3-D point cloud laser data collected from a moving platform in a urban environment.
  • [Robotic 3D Scan Repository] This repository provides 3D point clouds from robotic experiments,log files of robot runs and standard 3D data sets for the robotics community.
  • [Ford Campus Vision and Lidar Data Set] The dataset is collected by an autonomous ground vehicle testbed, based upon a modified Ford F-250 pickup truck.
  • [The Stanford Track Collection] This dataset contains about 14,000 labeled tracks of objects as observed in natural street scenes by a Velodyne HDL-64E S2 LIDAR.
  • [PASCAL3D+] Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild. [pos. det.]
  • [3D MNIST] The aim of this dataset is to provide a simple way to get started with 3D computer vision problems such as 3D shape recognition. [cls.]
  • [WAD] [ApolloScape] The datasets are provided by Baidu Inc. [tra. seg. det.]
  • [nuScenes] The nuScenes dataset is a large-scale autonomous driving dataset.
  • [PreSIL] Depth information, semantic segmentation (images), point-wise segmentation (point clouds), ground point labels (point clouds), and detailed annotations for all vehicles and people. [paper] [det. aut.]
  • [3D Match] Keypoint Matching Benchmark, Geometric Registration Benchmark, RGB-D Reconstruction Datasets. [reg. rec. oth.]
  • [BLVD] (a) 3D detection, (b) 4D tracking, (c) 5D interactive event recognition and (d) 5D intention prediction. [ICRA 2019 paper] [det. tra. aut. oth.]
  • [PedX] 3D Pose Estimation of Pedestrians, more than 5,000 pairs of high-resolution (12MP) stereo images and LiDAR data along with providing 2D and 3D labels of pedestrians. [ICRA 2019 paper] [pos. aut.]
  • [H3D] Full-surround 3D multi-object detection and tracking dataset. [ICRA 2019 paper] [det. tra. aut.]
  • [Argoverse BY ARGO AI] Two public datasets (3D Tracking and Motion Forecasting) supported by highly detailed maps to test, experiment, and teach self-driving vehicles how to understand the world around them.[CVPR 2019 paper][tra. aut.]
  • [Matterport3D] RGB-D: 10,800 panoramic views from 194,400 RGB-D images. Annotations: surface reconstructions, camera poses, and 2D and 3D semantic segmentations. Keypoint matching, view overlap prediction, normal prediction from color, semantic segmentation, and scene classification. [3DV 2017 paper] [code] [blog]
  • [SynthCity] SynthCity is a 367.9M point synthetic full colour Mobile Laser Scanning point cloud. Nine categories. [seg. aut.]
  • [Lyft Level 5] Include high quality, human-labelled 3D bounding boxes of traffic agents, an underlying HD spatial semantic map. [det. seg. aut.]
  • [SemanticKITTI] Sequential Semantic Segmentation, 28 classes, for autonomous driving. All sequences of KITTI odometry labeled. [ICCV 2019 paper] [seg. oth. aut.]
  • [NPM3D] The Paris-Lille-3D has been produced by a Mobile Laser System (MLS) in two different cities in France (Paris and Lille). [seg.]
  • [The Waymo Open Dataset] The Waymo Open Dataset is comprised of high resolution sensor data collected by Waymo self-driving cars in a wide variety of conditions. [det.]
  • [A*3D: An Autonomous Driving Dataset in Challeging Environments] A*3D: An Autonomous Driving Dataset in Challeging Environments. [det.]
  • [PointDA-10 Dataset] Domain Adaptation for point clouds.
  • [Oxford Robotcar] The dataset captures many different combinations of weather, traffic and pedestrians. [cls. det. rec.]
  • [PandaSet] Public large-scale dataset for autonomous driving provided by Hesai & Scale. It enables researchers to study challenging urban driving situations using the full sensor suit of a real self-driving-car. [det. seg.]
  • [3D-FRONT 3D-FUTURE] [Alibaba] 3D-FRONT contains 10,000 houses (or apartments) and ~70,000 rooms with layout information. 3D-FUTURE contains 20,000+ clean and realistic synthetic scenes in 5,000+ diverse rooms which contain 10,000+ unique high quality 3D instances of furniture.
  • [Campus3D] The Campus3D contains a photogrametry point cloud which has 931.7 million points, covering 1.58 km2 of 6 connected campus regions of NUS. The dataset are point-wisely annotated with a hierarchical structure of 24 semantic labels and contains 2,530 instances based on the labels. [MM 2020 paper][code][ det. cls. seg.]