└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # awesome-learned-point-cloud-compression 2 | 3 | [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) 4 | [![PR's Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat)](http://makeapullrequest.com) 5 | 6 | ## Papers 7 | 8 | ### 2024 9 | 10 | - [[TPAMI](https://ieeexplore.ieee.org/abstract/document/10682571)] A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding – Part I: Geometry. 11 | 12 | - [[TPAMI](https://ieeexplore.ieee.org/abstract/document/10682566)] A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding – Part II: Attribute. 13 | 14 | - [[TCSVT](https://ieeexplore.ieee.org/abstract/document/10530090)] Content-aware Rate Control for Geometry-based Point Cloud Compression. 15 | 16 | - [[ICASSP](https://ieeexplore.ieee.org/abstract/document/10445884)] Volumetric 3D Point Cloud Attribute Compression: Learned polynomial bilateral filter for prediction. 17 | 18 | - [[VCIP](https://ieeexplore.ieee.org/abstract/document/10402752)] Adaptive Entropy Coding of Graph Transform Coefficients for Point Cloud Attribute Compression. 19 | 20 | - [[arxiv](https://arxiv.org/abs/2404.07698)] Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator. 21 | 22 | - [[arxiv](https://arxiv.org/abs/2404.06936)] Efficient and Generic Point Model for Lossless Point Cloud Attribute Compression. [[Pytorch](https://github.com/I2-Multimedia-Lab/PoLoPCAC)] 23 | 24 | - [[MMVE](https://dl.acm.org/doi/abs/10.1145/3652212.3652217)] Progressive Coding for Deep Learning based Point Cloud Attribute Compression. 25 | 26 | - [[TMM](https://ieeexplore.ieee.org/abstract/document/10487884)] Multi-Space Point Geometry Compression with Progressive Relation-Aware Transformer. 27 | 28 | - [[ICASSP](https://ieeexplore.ieee.org/abstract/document/10448389)] Efficient Point Cloud Attribute Compression Using Rich Parallelizable Context Model. 29 | 30 | - [[ICASSP](https://ieeexplore.ieee.org/abstract/document/10445988)] Efficient Point Cloud Attribute Compression Framework using Attribute-Guided Graph Fourier Transform. 31 | 32 | - [[ICASSP](https://ieeexplore.ieee.org/abstract/document/10447944)] ScanPCGC: Learning-Based Lossless Point Cloud Geometry Compression using Sequential Slice Representation Encoding Auxiliary Information to Restore Compressed Point Cloud Geometry. 33 | 34 | - [[IET](https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.13139)] Point cloud geometry compression with sparse cascaded residuals and sparse attention. 35 | 36 | - [[ICASSP](https://ieeexplore.ieee.org/document/10446596)] NeRI: Implicit Neural Representation of LiDAR Point Cloud Using Range Image Sequence. [[Pytorch](https://github.com/RuixiangXue/NeRI)] 37 | 38 | - [[TVCG](https://ieeexplore.ieee.org/document/10470357)] Learning to Restore Compressed Point Cloud Attribute: A Fully Data-Driven Approach and A Rules-Unrolling-Based Optimization. 39 | 40 | ### 2023 41 | 42 | - [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Song_Efficient_Hierarchical_Entropy_Model_for_Learned_Point_Cloud_Compression_CVPR_2023_paper.html)] Efficient Hierarchical Entropy Model for Learned Point Cloud Compression. 43 | 44 | - [[TMM](https://doi.org/10.1109/TMM.2023.3331584)] Scalable Point Cloud Attribute Compression. 45 | 46 | - [[arxiv](https://doi.org/10.48550/arXiv.2303.06519)] Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model. 47 | 48 | - [[ICASSP](https://ieeexplore.ieee.org/document/10095385)] Deep probabilistic model for lossless scalable point cloud attribute compression. [[Pytorch](https://github.com/Weafre/MNeT/)] 49 | 50 | - [[DCC](https://ieeexplore.ieee.org/abstract/document/10125514)] Lossless Point Cloud Attribute Compression Using Cross-scale, Cross-group, and Cross-color Prediction. 51 | 52 | - [[ICASSP](https://ieeexplore.ieee.org/abstract/document/10096559)] Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention. 53 | 54 | - [[ACM MM](https://dl.acm.org/doi/abs/10.1145/3581783.3613793)] Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block. 55 | 56 | - [[ICASSP](https://ieeexplore.ieee.org/document/10096294/)] Normalizing Flow Based Point Cloud Attribute Compression. 57 | 58 | - [[APSIPA ASC](https://ieeexplore.ieee.org/document/10317255)] Sparse Tensor-based point cloud attribute compression using Augmented Normalizing Flows. 59 | 60 | - [[ACM MM](https://dl.acm.org/doi/abs/10.1145/3581783.3612422)] PDE-based Progressive Prediction Framework for Attribute Compression of 3D Point Clouds. [[C++](https://github.com/Yanggoo/PDE-basedPointCloudCompression)] 61 | 62 | - [[TIP](https://ieeexplore.ieee.org/document/10314418)] GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute. [[Pytorch](https://github.com/xjr998/GQE-Net)] 63 | 64 | - [[arixiv](https://arxiv.org/abs/2311.13539)] Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compression. 65 | 66 | - [[TIP](https://ieeexplore.ieee.org/document/10234082)] Near-Lossless Compression of Point Cloud Attribute Using Quantization Parameter Cascading and Rate-Distortion Optimization. 67 | 68 | - [[TPAMI](https://ieeexplore.ieee.org/document/10301698)] 3-D Point Cloud Attribute Compression With -Laplacian Embedding Graph Dictionary Learning. 69 | 70 | - [[TVCG](https://ieeexplore.ieee.org/document/10328911)] GRNet: Geometry Restoration for G-PCC Compressed Point Clouds Using Auxiliary Density Signaling. [[Pytorch](https://github.com/3dpcc/GRNet)] 71 | 72 | - [[CVM](https://arxiv.org/abs/2209.08276)] ARNet: Compression Artifact Reduction for Point Cloud Attribute. [[Pytorch](https://github.com/3dpcc/ARNet)] 73 | 74 | - [[TMM](https://ieeexplore.ieee.org/document/10313579)] ScalablePCAC: Scalable Point Cloud Attribute Compression. 75 | 76 | - [[ACM MM](https://dl.acm.org/doi/10.1145/3581783.3613847)] YOGA: Yet Another Geometry-based Point Cloud Compressor. [[Pytorch](https://github.com/3dpcc/YOGAv1)] 77 | 78 | - [[unpublished](https://3dpcc.github.io/publication/YOGAv2/)] YOGAv2: A Layered Point Cloud Compressor. 79 | 80 | ### 2022 81 | 82 | - [[TCSVT](https://ieeexplore.ieee.org/abstract/document/9852261)] Isolated Points Prediction via Deep Neural Network on Point Cloud Lossless Geometry Compression. 83 | 84 | - [[ARXIV](https://arxiv.org/abs/2208.12573)] Efficient LiDAR Point Cloud Geometry Compression Through Neighborhood Point Attention. 85 | 86 | - [[ARXIV](https://arxiv.org/abs/2208.02519)] IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression. [[Pytorch](https://github.com/I2-Multimedia-Lab/IPDAE)] 87 | 88 | - [[ICME](https://ieeexplore.ieee.org/abstract/document/9859853)] TDRNet: Transformer-Based Dual-Branch Restoration Network for Geometry Based Point Cloud Compression Artifacts. 89 | 90 | - [[ECCV](https://arxiv.org/abs/2205.00760)] Point Cloud Compression with Sibling Context and Surface Priors. [[Pytorch](https://github.com/zlichen/PCC-S)] 91 | 92 | - [[APCCPA](https://arxiv.org/abs/2209.04401)] GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression. [[Pytorch](https://github.com/InterDigitalInc/GRASP-Net)] 93 | 94 | - [[AAAI](https://arxiv.org/abs/2202.06028)] OctAttention: Octree-based Large-scale Context Model for Point Cloud Compression. [[Pytorch](https://github.com/zb12138/OctAttention)] 95 | 96 | - [[CVPR](http://arxiv.org/abs/2204.12684)] Density-preserving Deep Point Cloud Compression. [[Pytorch](https://github.com/yunhe20/D-PCC)] 97 | 98 | - [[CVPR](https://arxiv.org/abs/2203.09931)] 3DAC: Learning Attribute Compression for Point Clouds. [[Pytorch](https://github.com/fatPeter/ThreeDAC)] 99 | 100 | - [[ICMR](https://dl.acm.org/doi/abs/10.1145/3512527.3531423)] TransPCC: Towards Deep Point Cloud Compression via Transformers. [[Pytorch](https://github.com/jokieleung/TransPCC)] 101 | 102 | - [[APCCPA](https://dl.acm.org/doi/abs/10.1145/3552457.3555731)] Transformer and Upsampling-Based Point Cloud Compression. [[Pytorch](https://github.com/arsx958/PCT_PCC)] 103 | 104 | ### 2021 105 | 106 | - [[MM Asia](https://dl.acm.org/doi/abs/10.1145/3469877.3490611)] Patch-Based Deep Autoencoder for Point Cloud Geometry Compression. [[Pytorch](https://github.com/I2-Multimedia-Lab/PCC_Patch)] 107 | 108 | - [[TCSVT](https://ieeexplore.ieee.org/document/9321375)] Lossy Point Cloud Geometry Compression via End-to-End Learning. 109 | 110 | - [[DCC](https://ieeexplore.ieee.org/document/9418789)] Multiscale Point Cloud Geometry Compression. [[Pytorch](https://github.com/NJUVISION/PCGCv2)] [[Presentation](https://sigport.org/documents/multiscale-point-cloud-geometry-compression)] 111 | 112 | - [[DCC](https://ieeexplore.ieee.org/document/9418793)] Point AE-DCGAN: A deep learning model for 3D point cloud lossy geometry compression. [[Presentation](https://sigport.org/documents/point-ae-dcgan-deep-learning-model-3d-point-cloud-lossy-geometry-compression)] 113 | 114 | - [[CVPR](https://arxiv.org/abs/2105.02158)] VoxelContext-Net: An Octree based Framework for Point Cloud Compression. 115 | 116 | - [[ICASPP](https://ieeexplore.ieee.org/document/9414763)] Learning-Based Lossless Compression of 3D Point Cloud Geometry. [[Tensorflow](https://github.com/Weafre/VoxelDNN)] 117 | 118 | - [[RAL-ICRA](https://ieeexplore.ieee.org/document/9354895)] Deep Compression for Dense Point Cloud Maps. [[Pytorch](https://github.com/PRBonn/deep-point-map-compression)] 119 | 120 | - [[arXiv](https://arxiv.org/abs/2104.09859)] Multiscale deep context modeling for lossless point cloud geometry compression. [[Pytorch](https://github.com/Weafre/MSVoxelDNN)] 121 | 122 | - [[TCSVT](https://ieeexplore.ieee.org/abstract/document/9496667)] Lossless Coding of Point Cloud Geometry using a Deep Generative Model. [[Tensorflow](https://github.com/Weafre/VoxelDNN_v2)] 123 | 124 | - [[ICIP](https://ieeexplore.ieee.org/document/9506631)] Point Cloud Geometry Compression Via Neural Graph Sampling. 125 | 126 | ### 2020 127 | 128 | - [[ICME](https://ieeexplore.ieee.org/document/9102866)] Lossy Geometry Compression Of 3d Point Cloud Data Via An Adaptive Octree-Guided Network. [[Tensorflow](https://github.com/wxz1996/pc_compress)] 129 | 130 | - [[MMSP](https://ieeexplore.ieee.org/document/9287077)] Improved Deep Point Cloud Geometry Compression. [[Tensorflow](https://github.com/mauriceqch/pcc_geo_cnn_v2)] 131 | 132 | - [[CVPR](https://ieeexplore.ieee.org/document/9157381)] OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression. 133 | 134 | - [[NIPS](https://arxiv.org/abs/2011.07590)] MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models. 135 | 136 | - [[ICIP](https://ieeexplore.ieee.org/document/9191180)] Folding-Based Compression Of Point Cloud Attributes. [[Tensorflow](https://github.com/mauriceqch/pcc_attr_folding)] 137 | 138 | - [[ICIP](https://ieeexplore.ieee.org/document/9190647)] A Syndrome-Based Autoencoder For Point Cloud Geometry Compression. 139 | 140 | ### 2019 141 | 142 | - [[ICIP](https://ieeexplore.ieee.org/document/8803413)] Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression. [[Tensorflow](https://github.com/mauriceqch/pcc_geo_cnn)] 143 | 144 | - [[ICRA](https://ieeexplore.ieee.org/document/8794264)] Point Cloud Compression for 3D LiDAR Sensor using Recurrent Neural Network with Residual Blocks. [[PyTorch](https://github.com/ChenxiTU/Point-cloud-compression-by-RNN)] 145 | 146 | - [[PCS](https://ieeexplore.ieee.org/document/8954537)] Point cloud coding: Adopting a deep learning-based approach. 147 | 148 | - [[arXiv](https://arxiv.org/abs/1909.12037)] Learned point cloud geometry compression. 149 | 150 | - [[arXiv](https://arxiv.org/abs/1905.03691)] Deep autoencoder-based lossy geometry compression for point clouds. [[Tensorflow](https://github.com/YanWei123/Deep-AutoEncoder-based-Lossy-Geometry-Compression-for-Point-Clouds)] 151 | 152 | - [[CMM](https://dl.acm.org/doi/10.1145/3343031.3351061)] 3d point cloud geometry compression on deep learning. 153 | 154 | - [[TIP](https://ieeexplore.ieee.org/document/8676054)] A Volumetric Approach to Point Cloud Compression—Part I: Attribute Compression. 155 | 156 | - [[TIP](https://ieeexplore.ieee.org/document/8931233)] A Volumetric Approach to Point Cloud Compression–Part II: Geometry Compression. 157 | 158 | ### 2018 159 | 160 | - [[MM](https://dl.acm.org/doi/10.1145/3240508.3240696)] Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction. 161 | 162 | ### 2016 163 | 164 | - [[MM](https://ieeexplore.ieee.org/document/7405340)] Graph-based compression of dynamic 3D point cloud sequences. 165 | 166 | 167 | ## Others 168 | 169 | - [[Draco](https://github.com/google/draco)] Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics. 170 | 171 | - [[MPEG V-PCC](https://github.com/MPEGGroup/mpeg-pcc-tmc2)] MPEG Video codec based point cloud compression (V-PCC) test model (tmc2). 172 | 173 | - [[MPEG G-PCC](https://github.com/MPEGGroup/mpeg-pcc-tmc13)] MPEG Geometry based point cloud compression (G-PCC) test model (tmc13). 174 | 175 | - [[CAS '18](https://ieeexplore.ieee.org/document/8571288)] Emerging MPEG Standards for Point Cloud Compression. 176 | 177 | - [[EG '06](https://dl.acm.org/doi/10.5555/2386388.2386404)] Octree-based point-cloud compression. 178 | 179 | - [[ICRA '12](https://ieeexplore.ieee.org/document/6224647)] Real-time compression of point cloud streams. 180 | 181 | ### 2016 182 | 183 | - [[MM](https://ieeexplore.ieee.org/document/7482691)] Compression of 3D Point Clouds Using a Region-Adaptive Hierarchical Transform. 184 | 185 | ### 2018 186 | 187 | - [[ICIP](https://ieeexplore.ieee.org/document/8451802)] Intra-Frame Context-Based Octree Coding for Point-Cloud Geometry. 188 | 189 | ### 2020 190 | 191 | - [[IROS](https://ieeexplore.ieee.org/document/9341071)] Real-Time Spatio-Temporal LiDAR Point Cloud Compression. [[C++ '1](https://github.com/yaoli1992/LiDAR-Point-Cloud-Compression)] [[C++ '2](https://github.com/horizon-research/Real-Time-Spatio-Temporal-LiDAR-Point-Cloud-Compression)] 192 | 193 | ### 2021 194 | 195 | - [[TCSVT](https://ieeexplore.ieee.org/abstract/document/9503405)] Lossy Point Cloud Geometry Compression via Region-wise Processing. 196 | 197 | 198 | ## Datasets 199 | 200 | - [[KITTI](http://www.cvlibs.net/datasets/kitti/)] The KITTI Vision Benchmark Suite. 201 | 202 | - [[ShapeNet](https://shapenet.org/)] A collaborative dataset between researchers at Princeton, Stanford and TTIC. 203 | 204 | - [[ModelNet](https://modelnet.cs.princeton.edu/)] ModelNet Database. 205 | 206 | - [[JPEG Pleno](http://plenodb.jpeg.org/)] JPEG Pleno Database. 207 | 208 | - [[MVUB](http://plenodb.jpeg.org/pc/microsoft/)] Microsoft Voxelized Upper Bodies dataset. 209 | --------------------------------------------------------------------------------