Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/subeeshvasu/Awsome_Deep_Geometry_Learning

A list of resources about deep learning solutions on 3D shape processing
https://github.com/subeeshvasu/Awsome_Deep_Geometry_Learning
3d-models 3d-reconstruction 3d-representation 3d-shapes implicit-representions meshes point-cloud primitives shapes-learning voxels
Last synced: about 2 months ago
JSON representation
A list of resources about deep learning solutions on 3D shape processing
Host: GitHub
URL: https://github.com/subeeshvasu/Awsome_Deep_Geometry_Learning
Owner: subeeshvasu
Created: 2020-04-05T16:14:39.000Z (over 4 years ago)
Default Branch: master
Last Pushed: 2021-08-23T17:40:42.000Z (about 3 years ago)
Last Synced: 2024-04-11T03:55:39.765Z (5 months ago)
Topics: 3d-models, 3d-reconstruction, 3d-representation, 3d-shapes, implicit-representions, meshes, point-cloud, primitives, shapes-learning, voxels
Homepage:
Size: 1.5 MB
Stars: 332
Watchers: 30
Forks: 53
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

awesome-machine-learning-resources - **[List
awesome-computer-vision - Awsome Deep Geometry Learning
README

        A curated list of resources for Deep Geometry Learning

**Image-based methods**

+ 2012-NIPS - Convolutional-recursive deep learning for 3d object classification. [[Paper]](https://papers.nips.cc/paper/4773-convolutional-recursive-deep-learning-for-3d-object-classification.pdf)

+ 2014-NIPS - Depth map prediction from a single image using a multi-scale deep network. [[Paper]](https://arxiv.org/abs/1406.2283)

+ 2014-ECCV - Learning Rich Features from RGB-D Images for Object Detection and Segmentation. [[Paper]](https://arxiv.org/abs/1407.5736)

+ 2015-CVPR - Aligning 3D models to RGB-D images of cluttered scenes. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2015/papers/Gupta_Aligning_3D_Models_2015_CVPR_paper.pdf)

+ 2015-ICCV - Multi-view convolutional neural networks for 3d shape recognition. [[Paper]](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Su_Multi-View_Convolutional_Neural_ICCV_2015_paper.pdf)

+ 2016-CVPR - Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images. [[Paper]](http://dss.cs.princeton.edu/paper.pdf)

+ 2016-CVPR - Volumetric and multi-view cnns for object classification on 3d data. [[Paper]](https://arxiv.org/abs/1604.03265)

**Voxel-based methods**

***Dense Voxels***

+ 2015-CVPR - 3d shapenets: A deep representation for volumetric shapes. [[Paper]](https://people.csail.mit.edu/khosla/papers/cvpr2015_wu.pdf)

+ 2015-ICCV - Multi-view convolutional neural networks for 3d shape recognition. [[Paper]](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Su_Multi-View_Convolutional_Neural_ICCV_2015_paper.pdf)

+ 2015-IROS - Voxnet: A 3d convolutional neural network for real-time object recognition. [[Paper]](https://www.ri.cmu.edu/pub_files/2015/9/voxnet_maturana_scherer_iros15.pdf)

+ 2015-IROS - VoxNet: A 3D convolutional neural network for realtime object recognition. [[Paper]](https://www.ri.cmu.edu/pub_files/2015/9/voxnet_maturana_scherer_iros15.pdf)

+ 2016-CVPR - Volumetric and multi-view cnns for object classification on 3d data. [[Paper]](https://arxiv.org/abs/1604.03265)

+ 2016-ECCV - Vconv-DAE: Deep volumetric shape learning without object labels. [[Paper]](https://arxiv.org/abs/1604.03755)

+ 2016-ECCV - Learning a predictable and generative vector representation for objects. [[Paper]](https://arxiv.org/abs/1603.08637)

+ 2016-ECCV - 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. [[Paper]](https://arxiv.org/abs/1604.00449)

+ 2016-NIPS - Learning a probabilistic latent space of object shapes via 3D generative adversarial modeling. [[Paper]](https://papers.nips.cc/paper/6096-learning-a-probabilistic-latent-space-of-object-shapes-via-3d-generative-adversarial-modeling)[[Code]](https://github.com/zck119/3dgan-release)

+ 2017-BMVC - Orientation-boosted voxel nets for 3d object recognition. [[Paper]](https://arxiv.org/abs/1604.03351)

+ 2020 - UCLID-Net: Single View Reconstruction in Object Space. [[Paper]](https://arxiv.org/pdf/2006.03817.pdf)

+ 2020-ECCV - CoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470358.pdf)

+ 2020-ACCV - DeepVoxels++: Enhancing the Fidelity of Novel View Synthesis from 3D Voxel Embeddings. [[Paper]](https://openaccess.thecvf.com/content/ACCV2020/papers/He_DeepVoxels_Enhancing_the_Fidelity_of_Novel_View_Synthesis_from_3D_ACCV_2020_paper.pdf)

***Sparse Voxels***

+ 2016-NIPS - Fpnn: Field probing neural networks for 3d data. [[Paper]](https://arxiv.org/abs/1605.06240)

+ 2017-3DV - Hierarchical surface prediction for 3d object reconstruction. [[Paper]](https://arxiv.org/abs/1704.00710)

+ 2017-CVPR - Octnet: Learning deep 3d representations at high resolutions. [[Paper]](https://arxiv.org/abs/1611.05009)

+ 2017-ICCV - Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. [[Paper]](https://arxiv.org/abs/1703.09438)

+ 2017-TOG - O-cnn: Octree-based convolutional neural networks for 3d shape analysis. [[Paper]](https://arxiv.org/abs/1712.01537)

+ 2018-TOG - Adaptive O-CNN: A patch-based deep representation of 3D shapes. [[Paper]](https://arxiv.org/abs/1809.07917)

+ 2020-NIPS - Neural Sparse Voxel Fields. [[Paper]](https://arxiv.org/pdf/2007.11571.pdf)[[Code]](https://github.com/facebookresearch/NSVF)

+ 2020-TPAMI - Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis. [[Paper]](https://arxiv.org/abs/2012.13522)[[Code]](https://github.com/jianwen-xie/3DDescriptorNet)

**Surface-based representation**

***Point-based***

+ 2017-CVPR - A point set generation network for 3d object reconstruction from a single image. [[Paper]](https://arxiv.org/abs/1612.00603)

+ 2017-CVPR - Pointnet: Deep learning on point sets for 3d classification and segmentation. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Qi_PointNet_Deep_Learning_CVPR_2017_paper.pdf)

+ 2017-ICCV - Escape from cells: Deep kd-networks for the recognition of 3D point cloud models. [[Paper]](https://arxiv.org/abs/1704.01222)

+ 2017-NIPS - PointNet++: Deep hierarchical feature learning on point sets in a metric space. [[Paper]](https://papers.nips.cc/paper/7095-pointnet-deep-hierarchical-feature-learning-on-point-sets-in-a-metric-space.pdf)

+ 2018-CVPR - Foldingnet: Point cloud auto-encoder via deep grid deformation. [[Paper]](https://arxiv.org/abs/1712.07262)

+ 2018-CVPR - Point cloud upsampling network. [[Paper]](https://arxiv.org/abs/1801.06761)

+ 2018-CVPR - Sparse lattice networks for point cloud processing. [[Paper]](https://arxiv.org/abs/1802.08275)

+ 2018-CVPR - Tangent convolutions for dense prediction in 3d. [[Paper]](https://arxiv.org/abs/1807.02443) [[Tf-Code]](https://github.com/tatarchm/tangent_conv)

+ 2018-ICML - Learning Representations and Generative Models For 3D Point Clouds. [[Paper]](https://arxiv.org/abs/1707.02392) [[Tf-Code]](https://github.com/optas/latent_3d_points)

+ 2018 - Point Cloud GAN. [[Paper]](https://arxiv.org/abs/1810.05795) [[Py-Tf-Hybrid-Code]](https://github.com/chunliangli/Point-Cloud-GAN)

+ 2018-TOG - Point convolutional neural networks by extension operators. [[Paper]](https://arxiv.org/abs/1803.10091)

+ 2018-EuroGraph - PCPNet: Learning Local Shape Properties from Raw Point Clouds. [[Paper]](https://arxiv.org/abs/1710.04954)[[Code]](https://github.com/paulguerrero/pcpnet)

+ 2019-WACV - High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimization. [[Paper]](https://arxiv.org/pdf/1807.03407.pdf)

+ 2019-CVPR - Patch-based progressive 3D point set upsampling. [[Paper]](https://arxiv.org/abs/1811.11286)

+ 2019-CVPR - PU-GAN: a point cloud upsampling adversarial network. [[Paper]](https://arxiv.org/abs/1801.06761)

+ 2019-CVPR - PointConv: Deep Convolutional Networks on 3D Point Clouds. [[Paper]](https://arxiv.org/abs/1811.07246)[[Code]](https://github.com/DylanWusee/pointconv)

+ 2019-CVPR - Supervised Fitting of Geometric Primitives to 3D Point Clouds. [[Paper]](https://arxiv.org/abs/1811.08988)[[Code]](https://github.com/lingxiaoli94/SPFN)

+ 2019-CVPR - PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation. [[Paper]](https://arxiv.org/abs/1903.00709)[[Code]](https://github.com/FENGGENYU/PartNet)

+ 2019-CVPR - Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN. [[Paper]](https://arxiv.org/abs/1811.07782)

+ 2019-CVPR - PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing. [[Paper]](http://jiaya.me/papers/pointweb_cvpr19.pdf)[[Code]](https://github.com/hszhao/PointWeb)

+ 2019-ICCV - DiscoNet: Shapes learning on disconnected manifolds for 3D editing. [[Paper]](http://cedric.cnam.fr/~thomen/papers/Mehr_ICCV19.pdf)

+ 2019-ICCV - Interpolated Convolutional Networks for 3D Point Cloud Understanding. [[Paper]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Mao_Interpolated_Convolutional_Networks_for_3D_Point_Cloud_Understanding_ICCV_2019_paper.pdf)

+ 2019-NIPS - Point-Voxel CNN for Efficient 3D Deep Learning. [[Paper]](https://arxiv.org/abs/1907.03739)

+ 2019-TOG - LOGAN: Unpaired Shape Transform in Latent Overcomplete Space. [[Paper]](https://arxiv.org/abs/1903.10170)[[Code]](https://github.com/kangxue/LOGAN)

+ 2019 - ConvPoint: Continuous Convolutions for Point Cloud Processing. [[Paper]](https://arxiv.org/abs/1904.02375) [[Py-Code]](https://github.com/aboulch/ConvPoint)

+ 2019-CGF - PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds. [[Paper]](https://arxiv.org/abs/1901.01060)[[Code]](https://github.com/mrakotosaon/pointcleannet)

+ 2020-ICLR - Unpaired Point Cloud Completion on Real Scans using Adversarial Training. [[Paper]](https://arxiv.org/pdf/1904.00069.pdf)[[Code]](https://github.com/xuelin-chen/pcl2pcl-gan-pub)

+ 2020-CVPR - AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss. [[Paper]](https://arxiv.org/pdf/1903.10297.pdf)

+ 2020-CVPR - PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Shi_PV-RCNN_Point-Voxel_Feature_Set_Abstraction_for_3D_Object_Detection_CVPR_2020_paper.pdf)[[Code]](https://github.com/open-mmlab/OpenPCDet)

+ 2020-CVPR - Point Cloud Completion by Skip-attention Network with Hierarchical Folding. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2020/html/Wen_Point_Cloud_Completion_by_Skip-Attention_Network_With_Hierarchical_Folding_CVPR_2020_paper.html)

+ 2020-ICRA - Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. [[Paper]](https://arxiv.org/pdf/1907.12046.pdf)

+ 2020-ECCV - SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification. [[Paper]](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480069.pdf)

+ 2020-ECCV - Discrete Point Flow Networks for Efficient Point Cloud Generation. [[Paper]](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123680681.pdf)

+ 2020-ECCV - Learning Gradient Fields for Shape Generation. [[Paper]](https://arxiv.org/pdf/2008.06520.pdf)[[Code]](https://github.com/RuojinCai/ShapeGF)

+ 2020-ECCV - Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470647.pdf)[[Code]](https://github.com/mrakotosaon/intrinsic_interpolations)

+ 2020-ECCV - Quaternion Equivariant Capsule Networks for 3D Point Clouds. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123460001.pdf)

+ 2020-ECCV - SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480069.pdf)

+ 2020-ECCV - DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares. [[Paper]](https://arxiv.org/pdf/2003.10826.pdf)

+ 2020-ECCV - Multimodal Shape Completion via Conditional Generative Adversarial Networks. [[Paper]](https://arxiv.org/pdf/2003.07717.pdf)

+ 2020-ECCV - Detail Preserved Point Cloud Completion via Separated Feature Aggregation. [[Paper]](https://arxiv.org/pdf/2007.02374.pdf)[[Code]](https://github.com/XLechter/Detail-Preserved-Point-Cloud-Completion-via-SFA)

+ 2020-ECCV - Weakly-supervised 3D Shape Completion in the Wild. [[Papr]](https://arxiv.org/pdf/2008.09110.pdf)

+ 2020-3DV - KAPLAN: A 3D Point Descriptor for Shape Completion. [[Paper]](https://arxiv.org/pdf/2008.00096.pdf)

+ 2020-3DV - Self-Supervised Learning of Point Clouds via Orientation Estimation. [[Paper]](https://arxiv.org/pdf/2008.00305.pdf)[[Code]](https://github.com/OmidPoursaeed/Self_supervised_Learning_Point_Clouds)

+ 2020-NIPS - CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations. [Paper](https://arxiv.org/pdf/2008.02792.pdf)[[Code]](https://github.com/davrempe/caspr)

+ 2020-NIPS - Skeleton-bridged Point Completion: From Global Inference to Local Adjustment. [[Paper]](https://arxiv.org/pdf/2010.07428.pdf)

+ 2020-Arxiv - Point Cloud Completion by Learning Shape Priors. [[Paper]](https://arxiv.org/pdf/2008.00394.pdf)[[Code]](https://github.com/xiaogangw/point-cloud-completion-shape-prior)

+ 2020-Arxiv - CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling. [[Paper]](https://arxiv.org/pdf/2009.04660.pdf)[[Code]](https://github.com/JiehongLin/CAD-PU)

+ 2020-Arxiv - Hausdorff Point Convolution with Geometric Priors. [[Paper]](https://arxiv.org/pdf/2012.13118.pdf)

+ 2021-CVPR - PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. [[Paper]](https://arxiv.org/abs/2103.14635)[[Code]](https://github.com/CVMI-Lab/PAConv)

+ 2021-CG - LPMNet: Latent Part Modification and Generation for 3D Point Clouds. [[Paper]](https://arxiv.org/pdf/2008.03560.pdf)

+ 2021-CAD - Part-based data-driven 3D shape interpolation. [[Paper]](https://www.sciencedirect.com/science/article/pii/S0010448521000385)

+ 2021-TIP - SGAN: Hierarchical Graph Learning for Point Cloud Generation. [[Paper]](https://ieeexplore.ieee.org/abstract/document/9409723)

+ 2021-CVPR - Unsupervised 3D Shape Completion through GAN Inversion. [[Paper]](https://arxiv.org/pdf/2104.13366.pdf)

+ 2021-Arxiv - Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding. [[Paper]](https://arxiv.org/abs/2103.07838)

+ 2021-Arxiv - PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. [[Paper]](https://arxiv.org/pdf/2103.14635.pdf)

+ 2021-Arxiv - Potential Convolution: Embedding Point Clouds into Potential Fields. [[Paper]](https://arxiv.org/pdf/2104.01754.pdf)

***Mesh-based***

+ 2016-ECCV - Deep learning 3D shape surfaces using geometry images. [[Paper]](https://link.springer.com/chapter/10.1007/978-3-319-46466-4_14)

+ 2016-NIPS - Learning shape correspondence with anisotropic convolutional neural networks. [[Paper]](https://arxiv.org/abs/1605.06437)

+ 2017-TOG - Convolutional neural networks on surfaces via seamless toric covers. [[Paper]](http://www.vovakim.com/papers_small/17_SIGGRAPH_ToricCNN.pdf)

+ 2017-CVPR - Geometric deep learning on graphs and manifolds using mixture model cnns. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Monti_Geometric_Deep_Learning_CVPR_2017_paper.pdf)

+ 2017-ICCV - Directionally convolutional networks for 3D shape segmentation. [[Paper]](https://arxiv.org/abs/1605.06437)

+ 2018-CVPR - Feastnet: Feature-steered graph convolutions for 3d shape analysis. [[Paper]](https://arxiv.org/abs/1706.05206)

+ 2018-CVPR - SplineCNN: Fast geometric deep learning with continuous b-spline kernels. [[Paper]](https://arxiv.org/abs/1711.08920)

+ 2018-CVPR - AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation. [[Paper]](https://arxiv.org/abs/1802.05384)

+ 2018-ECCV - Pixel2Mesh: Generating 3D mesh models from single RGB images. [[Paper]](https://arxiv.org/abs/1804.01654)

+ 2018-Arxiv - Convolutional neural networks on 3d surfaces using parallel frames. [[Paper]](https://arxiv.org/abs/1808.04952)

+ 2019-TOG - MeshCNN: a network with an edge. [[Paper]](https://arxiv.org/abs/1809.05910)

+ 2019-ICCV - Pixel2Mesh++: Multi-view 3D mesh generation via deformation. [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wen_Pixel2Mesh_Multi-View_3D_Mesh_Generation_via_Deformation_ICCV_2019_paper.pdf)

+ 2019-ICCVW - Learning to Reconstruct Symmetric Shapes using Planar Parameterization of 3D Surface. [[Paper]](https://openaccess.thecvf.com/content_ICCVW_2019/papers/GMDL/Jain_Learning_to_Reconstruct_Symmetric_Shapes_using_Planar_Parameterization_of_3D_ICCVW_2019_paper.pdf)

+ 2020-ICML - Polygen: An autoregressive generative model of 3d meshes. [[Paper]](http://proceedings.mlr.press/v119/nash20a.html)[[Code]](https://github.com/deepmind/deepmind-research/tree/master/polygen)

+ 2020-ECCV - DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction. [[Paper]](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123660290.pdf)

+ 2020-ECCV - Weakly-supervised 3D Shape Completion in the Wild. [[Paper]](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123500273.pdf)

+ 2021-Arxiv - Learning Generative Models of Textured 3D Meshes from Real-World Images. [[Paper]](https://arxiv.org/pdf/2103.15627.pdf)

+ 2021-Arxiv - MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation. [[Paper]](https://arxiv.org/pdf/2105.13277.pdf)

**Implicit representation**

+ 2019-CVPR - Learning Implicit Fields for Generative Shape Modeling. [[Paper]](https://arxiv.org/abs/1812.02822) [[Code]](https://github.com/czq142857/implicit-decoder)

+ 2019-CVPR - Occupancy networks: Learning 3D reconstruction in function space. [[Paper]](https://arxiv.org/abs/1812.03828) [[Code]](https://github.com/autonomousvision/occupancy_networks)

+ 2019-CVPR - DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. [[Paper]](https://arxiv.org/abs/1901.05103) [[Code]](https://github.com/facebookresearch/DeepSDF)

+ 2019-ICCV - PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization. [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Saito_PIFu_Pixel-Aligned_Implicit_Function_for_High-Resolution_Clothed_Human_Digitization_ICCV_2019_paper.pdf)[[Code]](https://github.com/shunsukesaito/PIFu)

+ 2019-ICCV - Learning Shape Templates with Structured Implicit Functions. [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Genova_Learning_Shape_Templates_With_Structured_Implicit_Functions_ICCV_2019_paper.pdf)

+ 2019-NIPS - Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations. [[Paper]](http://papers.nips.cc/paper/8396-scene-representation-networks-continuous-3d-structure-aware-neural-scene-representations.pdf) (implicity not verified)

+ 2019-NIPS - DISN: Deep implicit surface network for high-quality single-view 3D reconstruction. [[Paper]](https://arxiv.org/abs/1905.10711) [[Code]](https://github.com/laughtervv/DISN)

+ 2019-NIPS - Learning to infer implicit surfaces without 3D supervision. [[Paper]](https://arxiv.org/abs/1911.00767)

+ 2019-Arxiv - Deep structured implicit functions. [[Paper]](https://arxiv.org/abs/1912.06126)

+ 2020-CVPR -  Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision. [[Paper]](http://www.cvlibs.net/publications/Niemeyer2020CVPR.pdf)[[Code]](https://github.com/autonomousvision/differentiable_volumetric_rendering)

+ 2020-CVPR - Dist: Rendering deep implicit signed distance function with differentiable sphere tracing. [[Paper]](http://b1ueber2y.me/projects/DIST-Renderer/dist-paper.pdf)[[Code]](https://github.com/B1ueber2y/DIST-Renderer)

+ 2020-CVPR - Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion. [[Paper]](https://virtualhumans.mpi-inf.mpg.de/papers/chibane20ifnet/chibane20ifnet.pdf)[[Code]](https://github.com/jchibane/if-net)

+ 2020-CVPR - Local implicit grid representations for 3d scenes. [[Paper]](https://arxiv.org/abs/2003.08981)[[Code]](https://github.com/tensorflow/graphics/tree/master/tensorflow_graphics/projects/local_implicit_grid)

+ 2020-CVPR - Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization. [[Paper]](https://arxiv.org/abs/2004.00452)[[Code]](https://shunsukesaito.github.io/PIFuHD/)

+ 2020-CVPR - SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization. [[Paper]](https://arxiv.org/abs/1912.07109)[[Code]](https://github.com/YueJiang-nj/CVPR2020-SDFDiff)

+ 2020-ECCV - Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction. [[Paper]](https://arxiv.org/abs/2003.10983)

+ 2020-ECCV - Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction. [[Paper]](https://arxiv.org/pdf/2007.11432.pdf)[[Code]](https://github.com/bharat-b7/IPNet)

+ 2020-ECCV - Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123460239.pdf)

+ 2020-ECCV - Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images. [[Paper]](https://arxiv.org/abs/2008.07760)

+ 2020-ECCV - Points2Surf: Learning Implicit Surfaces from Point Cloud Patches. [[Paper]](https://arxiv.org/abs/2007.10453)[[Code]](https://github.com/ErlerPhilipp/points2surf)

+ 2020-ECCV - Curriculum DeepSDF. [[Paper]](https://arxiv.org/abs/2003.08593)[[Code]](https://github.com/haidongz-usc/Curriculum-DeepSDF)

+ 2020-ECCV - Convolutional occupancy networks. [[Paper]](https://arxiv.org/abs/2003.04618)[[Code]](https://github.com/autonomousvision/convolutional_occupancy_networks)

+ 2020-NIPS - Neural Unsigned Distance Fields for Implicit Function Learning. [[Paper]](https://arxiv.org/pdf/2010.13938.pdf)

+ 2020-NIPS - Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence. [[Paper]](https://arxiv.org/pdf/2010.12320.pdf)

+ 2020-NIPS - Implicit Neural Representations with Periodic Activation Functions. [[Paper]](https://arxiv.org/abs/2006.09661)[[Code]](https://github.com/vsitzmann/siren)

+ 2020-NIPS - Fourier features let networks learn high frequency functions in low dimensional domains. [[Paper]](https://arxiv.org/pdf/2006.10739.pdf)[[Code]](https://github.com/tancik/fourier-feature-networks)

+ 2020-NIPS - MeshSDF: Differentiable Iso-Surface Extraction. [[Paper]](https://arxiv.org/pdf/2006.03997.pdf)[[Code]](https://github.com/cvlab-epfl/MeshSDF)

+ 2020 - PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations. [[Paper]](http://gvv.mpi-inf.mpg.de/projects/PatchNets/data/paper.pdf)

+ 2020-Arxiv - SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images. [[Paper]](https://arxiv.org/pdf/2008.05742.pdf)

+ 2020-Arxiv - Implicit Feature Networks for Texture Completion from Partial 3D Data. [[Paper]](https://arxiv.org/pdf/2009.09458.pdf)

+ 2020-Arxiv - Overfit Neural Networks as a Compact Shape Representation. [[Paper]](https://arxiv.org/pdf/2009.09808.pdf)

+ 2020-MM - Vaccine-style-net: Point Cloud Completion in Implici Continuous Function Space. [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3394171.3413648)

+ 2020-Arxiv - Learning Occupancy Function from Point Clouds for Surface Reconstruction. [[Paper]](https://arxiv.org/pdf/2010.11378.pdf)

+ 2020-Arxiv - DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces. [[Paper]](https://arxiv.org/abs/2011.02570)

+ 2020-Arxiv - NeuralFusion: Online Depth Fusion in Latent Space. [[Paper]](https://arxiv.org/pdf/2011.14791.pdf)

+ 2021-CVPR - Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations. [[Paper]](https://arxiv.org/pdf/2012.06434.pdf)

+ 2021-CVPR - Deep Implicit Templates for 3D Shape Representation. [[Paper]](https://arxiv.org/pdf/2011.14565.pdf)

+ 2021-CVPR - Deep Implicit Moving Least-Squares Functions for 3D Reconstruction. [[Paper]](https://arxiv.org/pdf/2103.12266.pdf)

+ 2021-CVPR - 3D Shape Generation With Grid-Based Implicit Functions.

+ 2021-Arxiv - Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes. [[Paper]](https://arxiv.org/pdf/2101.10994.pdf)[[Code]](https://github.com/nv-tlabs/nglod)

+ 2021-Arxiv - Secrets of 3D Implicit Object Shape Reconstruction in the Wild. [[Paper]](https://arxiv.org/pdf/2101.06860.pdf)

+ 2021-Arxiv - Generative Models as Distributions of Functions. [[paper]](https://arxiv.org/pdf/2102.04776.pdf)

+ 2021-Arxiv - Shelf-Supervised Mesh Prediction in the Wild. [[Paper]](https://arxiv.org/pdf/2102.06195.pdf)

+ 2021-Arxiv - Holistic 3D Scene Understanding from a Single Image with Implicit Representation. [[Paper]](https://arxiv.org/abs/2103.06422)

+ 2021-Arxiv - Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches. [[Paper]](https://arxiv.org/pdf/2104.00482.pdf)

+ 2021-Arxiv - A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation. [[Paper]](https://arxiv.org/pdf/2104.07645.pdf)[[Code]](https://jitengmu.github.io/A-SDF/)

+ 2021-Arxiv - Signed Distance Function Computation from an Implicit Surface. [[Paper]](https://arxiv.org/pdf/2104.08057.pdf)

+ 2021-Arxiv - Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields. [[Paper]](https://arxiv.org/pdf/2106.01553.pdf)

+ 2021-Arxiv - Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields. [[Paper]](https://arxiv.org/pdf/2106.05187.pdf)

+ 2021-Arxiv - A Deep Signed Directional Distance Function for Object Shape Representation. [[Paper]](https://arxiv.org/pdf/2107.11024.pdf)

**Structure/Part-based representation**

+ 2011-EG - Symmetry hierarchy of man-made objects. [[Paper]](https://kevinkaixu.net/papers/wang_eg11_symh.pdf)

+ 2014-TOG - Structure-aware shape processing. [[Paper]](http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/structure_survey/paper_docs/StructureAwareShapeProcessing_eg13.pdf)

+ 2015-CGF - Analysis and synthesis of 3d shape families via deep-learned generative models of surfaces. [[Paper]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.708.5905&rep=rep1&type=pdf)

+  2017-CGF - The shape variational autoencoder: A deep generative model of part-segmented 3d objects. [[Paper]](https://homepages.inf.ed.ac.uk/ckiw/postscript/sgp2017.pdf)

+  2018-TOG - Global-to-local generative model for 3d shapes. [[Paper]](https://vcc.tech/file/upload_file//image/research/att201810171620/G2L.pdf)[[Tf-Code]](https://github.com/Hao-HUST/G2LGAN/tree/master/Part%20Refiner)

+ 2019-ICCV - Composite Shape Modeling via Latent Space Factorization. [[Paper]](https://arxiv.org/abs/1901.02968)

+ 2019 - Learning structural graph layouts and 3d shapes for long span bridges 3d reconstruction. [[Paper]](https://arxiv.org/abs/1907.03387)

+  2019-ICCV - CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition. [[Paper]](https://arxiv.org/pdf/1811.07441.pdf)[[Tf-Code]](https://github.com/nschor/CompoNet)

+ 2019-ICCV - BAE-NET: Branched Autoencoder for Shape Co-Segmentation. [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_BAE-NET_Branched_Autoencoder_for_Shape_Co-Segmentation_ICCV_2019_paper.pdf)[[Tf-Code]](https://github.com/czq142857/BAE-NET)

+  2019-TOG - Structurenet: Hierarchical graph networks for 3d shape generation. [[Paper]](https://arxiv.org/abs/1908.00575) [[Tf-Code]](https://github.com/daerduoCarey/structurenet)

+ 2019-TOG - SAGNet: Structure-aware Generative Network for 3D-Shape Modeling. [[Paper]](https://arxiv.org/abs/1808.03981) [[Tf-Code]](https://github.com/zhijieW94/SAGNet)

+ 2019-TOG - SDM-NET: Deep generative network for structured deformable mesh. [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3355089.3356488) [[Code]](http://geometrylearning.com/sdm-net/)

+ 2020-AAAI - Learning part generation and assembly for structure-aware shape synthesis. [[Paper]](https://arxiv.org/abs/1906.06693)

+ 2020-CVPR - BSP-Net: Generating compact meshes via binary space partitioning. [[Paper]](https://arxiv.org/abs/1911.06971)[[Code]](https://github.com/czq142857/BSP-NET-original)

+ 2020-CVPR - PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes. [[Paper]](https://arxiv.org/abs/1911.10949)[[Code]](https://github.com/ChrisWu1997/PQ-NET)

+ 2020-CVPR - SSRNet: Scalable 3D Surface Reconstruction Network. [Paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Mi_SSRNet_Scalable_3D_Surface_Reconstruction_Network_CVPR_2020_paper.pdf)

+ 2020-CVPR - Neural Implicit Embedding for Point Cloud Analysis. [Paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Fujiwara_Neural_Implicit_Embedding_for_Point_Cloud_Analysis_CVPR_2020_paper.pdf)

+ 2020-CVPR - FroDO: From Detections to 3D Objects. [Paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Runz_FroDO_From_Detections_to_3D_Objects_CVPR_2020_paper.pdf)

+ 2020-CVPR - StructEdit: Learning Structural Shape Variations. [[Paper]](https://arxiv.org/abs/1911.11098)[[Code]](https://github.com/daerduoCarey/structedit)

+ 2020-SigAsia - ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis. [[Paper]](https://arxiv.org/abs/2009.08026)[[Code]](https://github.com/rkjones4/shapeAssembly)

+ 2020-Arxiv - A Simple and Scalable Shape Representation for 3D Reconstruction. [[Paper]](https://arxiv.org/pdf/2005.04623.pdf)

+ 2020-Arxiv - Topology-Aware Single-Image 3D Shape Reconstruction. [[Paper]](http://pages.ucsd.edu/~ztu/publication/L3DGM20_TPWCoder.pdf)

+ 2020-Arxiv - Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning. [Paper](https://arxiv.org/pdf/2006.02598.pdf)

+ 2020-Arxiv - COALESCE: Component Assembly by Learning to Synthesize Connections. [Paper](https://arxiv.org/pdf/2008.01936.pdf)

+ 2020-Arxiv - DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry. [[Paper]](https://arxiv.org/pdf/2008.05440.pdf)

+ 2020-ECCV - GSIR: Generalizable 3D Shape Interpretation and Reconstruction. [[Paper]](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123580494.pdf)

+ 2020-ECCV - Learning 3D Part Assembly from a Single Image. [[Paper]](https://arxiv.org/abs/2003.09754)[[Code]](https://github.com/AntheaLi/3DPartAssembly)

+ 2020-Arxiv - TM-NET: Deep Generative Networks for Textured Meshes. [[Paper]](https://arxiv.org/pdf/2010.06217.pdf)

+ 2021-CAD - Part-based data-driven 3D shape interpolation. [[Paper]](https://arxiv.org/pdf/2104.01754.pdf)

+ 2021-CVPR - Physically-aware Generative Network for 3D Shape Modeling. [[Paper]](http://www.lix.polytechnique.fr/~maks/papers/CVPR21_Phys_Gen_Networks.pdf)

+ 2021-Arxiv - Towards Generalising Neural Implicit Representations. [[Paper]](https://arxiv.org/pdf/2101.12690.pdf)

+ 2021- Extending StructureNet to Generate Physically Feasible 3D Shapes. [[Paper]](https://www.scitepress.org/Papers/2021/102567/102567.pdf)

+ 2021- How to represent part-whole hierarchies in a neural network. [[Paper]](https://arxiv.org/pdf/2102.12627.pdf)

+ 2021-Arxiv - Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation. [[Paper]](https://arxiv.org/pdf/2104.01148.pdf)

+ 2021-Arxiv - Spectral Unions of Partial Deformable 3D Shapes. [[Paper]](https://arxiv.org/pdf/2104.00514.pdf)

+ 2021-Arxiv - RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly. [[Paper]](https://arxiv.org/pdf/2107.12859.pdf)

**Deformation-based methods**

+ 2016-TOG - Efficient and flexible deformation representation for data-driven surface modeling. [[Paper]](https://dl.acm.org/doi/pdf/10.1145/2908736)

+ 2018-CVPR - Variational autoencoders for deforming 3d mesh models. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tan_Variational_Autoencoders_for_CVPR_2018_paper.pdf)

+ 2019-TVCG - Sparse data driven mesh deformation. [[Paper]](https://arxiv.org/abs/1709.01250)

+ 2018-AAAI - Mesh-based autoencoders for localized deformation component analysis. [[Paper]](https://arxiv.org/abs/1709.04304)

+ 2018-TOG - Automatic unpaired shape deformation transfer. [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3272127.3275028)

+ 2019-Arxiv - NASA: Neural articulated shape approximation. [[Paper]](https://arxiv.org/abs/1912.03207)

+ 2020-ECCV - LIMP: Learning Latent Shape Representations with Metric Preservation Priors. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480018.pdf)

+ 2020-Siggraph - Point2Mesh: A Self-Prior for Deformable Meshes. [[Paper]](https://arxiv.org/abs/2005.11084)[[Code]](https://github.com/ranahanocka/point2mesh)

+ 2020-Arxiv - Better Patch Stitching for Parametric Surface Reconstruction. [[Paper]](https://arxiv.org/pdf/2010.07021.pdf)

+ 2020-NIPS - ShapeFlow: Learnable Deformations Among 3D Shapes. [[Paper]](https://arxiv.org/pdf/2006.07982.pdf)

+ 2020-ECCV - NASA Neural Articulated Shape Approximation. [[Paper]](https://arxiv.org/pdf/1912.03207.pdf)

+ 2021-Arxiv - NPMs: Neural Parametric Models for 3D Deformable Shapes. [[Paper]](https://arxiv.org/pdf/2104.00702.pdf)

**Primitve-based methods**

+ 1971-CSSC - Visual perception by computer.

+ 1986-TOG -  Constructive solid geometry for polyhedral objects. [[Paper]](http://cs.brown.edu/people/jhughes/papers/Laidlaw-CSG-1986/paper.pdf)

+ 2016 - Volumetric Hierarchical Approximate Convex Decomposition. [[Paper]](https://www.taylorfrancis.com/books/9780429183911/chapters/10.1201/b21177-15)

+ 2017-CVPR -  Learning shape abstractions by assembling volumetric primitives. [[Paper]](https://arxiv.org/abs/1612.00404)[[Code]](https://github.com/shubhtuls/volumetricPrimitives)[[Py-Code]](https://github.com/nileshkulkarni/volumetricPrimitivesPytorch)

+ 2017-ICCV -  3dprnn: Generating shape primitives with recurrent neural networks. [[Paper]](https://arxiv.org/abs/1708.01648)[[Code]](https://github.com/zouchuhang/3D-PRNN)

+ 2017-TOG - GRASS: Generative recursive autoencoders for shape structures. [[Paper]](https://arxiv.org/abs/1705.02090)[[Code]](https://github.com/junli-lj/Grass)[[Py-Code]](https://github.com/kevin-kaixu/grass_pytorch)

+ 2017-TOG - ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling. [[Paper]](https://arxiv.org/pdf/1708.01841.pdf)[[Code]](https://github.com/mhsung/complement-me)

+ 2018-CVPR - Csgnet: Neural shape parser for constructive solid geometry. [[Paper]](https://arxiv.org/abs/1712.08290)[[Code]](https://github.com/Hippogriff/3DCSGNet)

+ 2018-CVPR - Im2struct: Recovering 3d shape structure from a single RGB image. [[Paper]](https://arxiv.org/abs/1804.05469)[[Code]](https://github.com/chengjieniu/Im2Struct)

+ 2018-ECCV - Physical Primitive Decomposition. [[Paper]](https://arxiv.org/pdf/1809.05070.pdf)

+ 2018-NIPS - Learning to Infer Graphics Programs from Hand-Drawn Images. [[Paper]](https://arxiv.org/pdf/1707.09627.pdf)[[Code]](https://github.com/ellisk42/TikZ)

+ 2018-SigAsia - FrankenGAN: Guided Detail Synthesis for Building Mass Models Using Style-Synchonized GANs. [[Paper]](https://arxiv.org/abs/1806.07179)[[Code]](https://github.com/twak/chordatlas)

+ 2018-TOG - InverseCSG: Automatic Conversion of 3D Models to CSG Trees. [[Paper]](http://people.csail.mit.edu/taodu/csg/paper.pdf)

+ 2018-3DV - Parsing Geometry Using Structure-Aware Shape Templates. [[Paper]](https://arxiv.org/pdf/1808.01337.pdf)[[Code]](https://github.com/vigansub/StructureAwareShapeTemplates)

+ 2018-ACCV - Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings. [[Paper]](https://arxiv.org/abs/1803.08495)[[Code]](https://github.com/kchen92/text2shape/)

+ 2019-CVPR - Supervised fitting of geometric primitives to 3d point clouds. [[Paper]](https://arxiv.org/abs/1811.08988)[[Code]](https://github.com/lingxiaoli94/SPFN)

+ 2019-CVPR - Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids. [[Paper]](https://arxiv.org/abs/1904.09970)[[Code]](https://github.com/paschalidoud/superquadric_parsing)

+ 2019-CVPR - Unsupervised Primitive Discovery for Improved 3D Generative Modeling. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Khan_Unsupervised_Primitive_Discovery_for_Improved_3D_Generative_Modeling_CVPR_2019_paper.pdf)

+ 2019-ICCV - Learning Shape Templates with Structured Implicit Functions. [[Paper]](https://arxiv.org/abs/1904.06447)[[Code]](https://github.com/google/ldif)

+ 2019-NIPS - Learning elementary structures for 3d shape generation and matching. [[Paper]](https://arxiv.org/abs/1908.04725)[[Code]](https://github.com/TheoDEPRELLE/AtlasNetV2)

+ 2019-ICLR - Learning to Infer and Execute 3D Shape Programs. [[Paper]](https://arxiv.org/abs/1901.02875)[[Code]](https://github.com/HobbitLong/shape2prog)

+ 2019-IJCV - Learning Single-Image 3D Reconstruction by Generative Modelling of Shape, Pose and Shading. [[Paper]](https://arxiv.org/abs/1901.06447)[[Code]](https://github.com/pmh47/dirt)

+ 2019-IGARSS - Primitive-Based 3D Building Modeling, Sensor Simulation, and Estimation. [[Paper]](https://arxiv.org/pdf/1901.05554.pdf)

+ 2019-TOG - Learning Adaptive Hierarchical Cuboid Abstractions of 3D Shape Collections. [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3355089.3356529?casa_token=LKGGa6x3o8oAAAAA:jReNOIlzvfBitCy_9bDr8IOglHxAjPs8fw1qcAIcKo3aGH9x2OP58bdaNKGDfbeBEiG9AmVouOylFw)[[Code]](https://github.com/isunchy/cuboid_abstraction)

+ 2019-TPAMI - PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models. [[Paper]](https://arxiv.org/pdf/1910.06511.pdf)

+ 2020-CVPR - Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image. [[Paper]](https://arxiv.org/abs/2004.01176)[[Code]](https://github.com/paschalidoud/hierarchical_primitives)

+ 2020-CVPR - DualSDF: Semantic Shape Manipulation using a Two-Level Representation. [[Paper]](https://arxiv.org/pdf/2004.02869.pdf)[[Code]](https://github.com/zekunhao1995/DualSDF)

+ 2020-CVPR - CvxNet: Learnable Convex Decomposition. [[Paper]](https://arxiv.org/abs/1909.05736)[[Code]](https://github.com/tensorflow/graphics/tree/master/tensorflow_graphics/projects/cvxnet)

+ 2020-CVPR - Local Deep Implicit Functions for 3D Shape. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/papers/Genova_Local_Deep_Implicit_Functions_for_3D_Shape_CVPR_2020_paper.pdf)[[Code]](https://github.com/google/ldif)

+ 2020-CVPR - Deep Parametric Shape Predictions using Distance Fields. [[Paper]](https://arxiv.org/abs/1904.08921)[[Code]](https://github.com/dmsm/DeepParametricShapes)

+ 2020-CVPR - Learning Generative Models of Shape Handles. [[Paper]](https://arxiv.org/abs/2004.03028)

+ 2020-CVPR - Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors. [[Paper]](https://arxiv.org/abs/1911.11288)[[Code]](https://github.com/TRI-ML/sdflabel)

+ 2020-ECCV - ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds. [[Paper]](https://arxiv.org/pdf/2003.12181.pdf)[[Code]](https://github.com/Hippogriff/parsenet-codebase)

+ 2020-ECCV - Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions. [[Paper]](https://arxiv.org/abs/2003.13834)[[Code]](https://github.com/matheusgadelha/PointCloudLearningACD)

+ 2020-BMVC - 3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture. [[Paper]](https://arxiv.org/pdf/1912.04663.pdf)

+ 2020-IWOBI - Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study. [[Paper]](https://arxiv.org/pdf/1904.06585.pdf)

+ 2020-NIPS - Neural Star Domain as Primitive Representation. [[Paper]](https://arxiv.org/pdf/2010.11248.pdf)

+ 2020-NIPS - PIE-NET: Parametric Inference of Point Cloud Edges. [[Paper]](https://arxiv.org/pdf/2007.04883.pdf)[[Code]](https://sites.google.com/site/alimahdaviamiri/projects/pie_net)

+ 2020-NIPS - UCSG-NET - Unsupervised Discovering of Constructive Solid Geometry Tree. [[Paper]](https://arxiv.org/pdf/2006.09102.pdf)[[Code]](https://github.com/kacperkan/ucsgnet/)

+ 2020-CGF - Learning Generative Models of 3D Structures. [[Paper]](https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.14020?casa_token=CPcce40KgkgAAAAA:IK3f0Aof3GE5XQgnCrzVeaFBhxM9jhyOH320rq_DhrHJe517YvbBhKivbXV05IUAhOXRlStCyBC7dIQ)

+ 2020 - Geometric Primitives in LiDAR Point Clouds: A Review. [[Paper]](https://ieeexplore.ieee.org/document/8977383)

+ 2020 - Unsupervised Deep Learning for Primitive-Based Shape Abstraction. [[Paper]](https://www.diva-portal.org/smash/get/diva2:1411556/FULLTEXT01.pdf)

+ 2020 - Dynamic Plane Convolutional Occupancy Networks. [[Paper]](https://arxiv.org/pdf/2011.05813.pdf)

+ 2020-Arxiv - Learning to Infer Shape Programs Using Latent Execution Self Training. [[Paper]](https://arxiv.org/pdf/2011.13045.pdf)

+ 2020-IEEEAccess - Learning to predict superquadric parameters from depth images with explicit and implicit supervision. [[Paper]](https://ieeexplore.ieee.org/abstract/document/9274424)

+ 2021 - Facilitated editing of generative design geometry in computer aided design user interface. [[Paper]](https://patentimages.storage.googleapis.com/dc/5f/93/dabb0864a9bfaa/US20200151953A1.pdf)

+ 2021-CVPR - Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks. [[Paper]](https://arxiv.org/pdf/2103.10429.pdf)[[Code]](https://paschalidoud.github.io/neural_parts)

+ 2021-CVPR - Inferring CAD Modeling Sequences Using Zone Graphs. [[Paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Xu_Inferring_CAD_Modeling_Sequences_Using_Zone_Graphs_CVPR_2021_paper.pdf)

+ 2021-CVPR - Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images. [[Paper]](https://arxiv.org/pdf/2105.02047.pdf)

+ 2021-Arxiv - Mixture of Volumetric Primitives for Efficient Neural Rendering. [[Paper]](https://arxiv.org/pdf/2103.01954.pdf)

+ 2021-Arxiv - EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation. [[Paper]](https://arxiv.org/pdf/2103.02517.pdf)

+ 2021- A deep neural network based shape unification to define a 3-Dimensional shape. [[Paper]](https://www.sciencedirect.com/science/article/pii/S221478532040848X). [[Paper]]()

+ 2021-Arxiv - On the Complexity of the CSG Tree Extraction Problem. [[Paper]](https://arxiv.org/abs/2103.06139)

+ 2021-Arxiv - Mixture of Volumetric Primitives for Efficient Neural Rendering. [[Paper]](https://arxiv.org/pdf/2103.01954.pdf)

+ 2021-Arxiv - ShapeMOD: Macro Operation Discovery for 3D Shape Programs. [[Paper]](https://arxiv.org/pdf/2104.06392.pdf)

+ 2021-Arxiv - Engineering Sketch Generation for Computer-Aided Design. [[Paper]](https://arxiv.org/pdf/2104.09621.pdf)

+ 2021-Arxiv - Fit4CAD: A point cloud benchmark for fitting simple geometric primitives in CAD models. [[Paper]](https://arxiv.org/pdf/2105.06858.pdf)

+ 2021-Arxiv - DeepCAD: A Deep Generative Network for Computer-Aided Design Models. [[Paper]](https://arxiv.org/pdf/2105.09492.pdf)

+ 2021-Arxiv - HPNet: Deep Primitive Segmentation Using Hybrid Representations. [[Paper]](https://arxiv.org/pdf/2105.10620.pdf)

+ 2021-Arxiv - Boundary-Sampled Halfspaces: A New Representation for Constructive Solid Modeling. [[Paper]](https://www.researchgate.net/profile/Xingyi_Du3/publication/351787830_Boundary-Sampled_Halfspaces_A_New_Representation_for_Constructive_Solid_Modeling/links/60aadb7092851ca9dcddaf64/Boundary-Sampled-Halfspaces-A-New-Representation-for-Constructive-Solid-Modeling.pdf)

+ 2021-Arxiv - SketchGen: Generating Constrained CAD Sketches. [[Paper]](https://arxiv.org/pdf/2106.02711.pdf)

+ 2021-Arxiv - Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds. [[Paper]](https://arxiv.org/pdf/2106.03437.pdf)

+ 2021-Arxiv - Creating 3d Shape Abstractions Using Superquadric Surfaces. [[Paper]](https://nemertes.library.upatras.gr/jspui/bitstream/10889/14977/3/Nemertes_Fotis%28ele%29.pdf)

+ 2021-CAD - Learning Cuboid Abstraction of 3D Shapes via Iterative Error Feedback. [[Paper]](https://www.sciencedirect.com/science/article/pii/S0010448521001032)

+ 2021-Arxiv - Discovering 3D Parts from Image Collections. [[Paper]](https://arxiv.org/pdf/2107.13629.pdf)

+ 2021-Arxiv - ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description. [[Paper]](https://arxiv.org/pdf/2108.00355.pdf)

**Survey Papers**

+ 2019-Arxiv - Deep learning for 3D point clouds: A survey. [[Paper]](https://arxiv.org/abs/1912.12033)

+ 2020-Arxiv - A Survey on Deep Geometry Learning: From a Representation Perspective. [[Paper]](https://arxiv.org/abs/2002.07995)

+ 2020-Arxiv - Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era. [[Paper]](https://arxiv.org/pdf/1906.06543.pdf)

+ 2020-MTA - Single image 3D object reconstruction based on deep learning: A review. [[Paper]](https://link.springer.com/article/10.1007/s11042-020-09722-8)

+ 2020-CG - Single-View 3D reconstruction: A Survey of deep learning methods. [[Paper]](https://www.sciencedirect.com/science/article/abs/pii/S0097849320301849)

+ 2021-Arxiv - Attention Models for Point Clouds in Deep Learning: A Survey. [[Paper]](https://arxiv.org/pdf/2102.10788.pdf)

+ 2021-MTA - A survey of recent 3D scene analysis and processing methods. [[Paper]](https://link.springer.com/article/10.1007/s11042-021-10615-7)

+ 2021-Arxiv - A comprehensive survey on point cloud registration. [[Paper]](https://arxiv.org/pdf/2103.02690.pdf)

+ 2021-Arxiv - 3D Semantic Scene Completion: a Survey. [[Paper]](https://arxiv.org/pdf/2103.07466.pdf)

+ 2021-Arxiv - A Revisit of Shape Editing Techniques: from the Geometric to the Neural Viewpoint. [[Paper]](https://arxiv.org/pdf/2103.01694.pdf)

**Misc**

+ Learning to Generate 3D Training Data - [[Thesis]](https://deepblue.lib.umich.edu/bitstream/handle/2027.42/163240/ydawei_1.pdf?sequence=1&isAllowed=y)

+ 2020-Arxiv - Deep Optimized Priors for 3D Shape Modeling and Reconstruction. [[Paper]](https://arxiv.org/pdf/2012.07241.pdf)

**Datasets**

+ 2019-ICCV - ShapeGlot: Learning Language for Shape Differentiation. [[Paper]](https://arxiv.org/pdf/1905.02925.pdf)[[Dataset]](http://ai.stanford.edu/~optas/shapeglot/)

***Part Labels***

+ 2009-SMI - A framework for the objective evaluation of segmentation algorithms using a ground-truth of human segmented 3D-models. [[Paper]](https://ieeexplore.ieee.org/document/5170161)[[Dataset]](http://193.48.251.101:8080/3dsegbenchmark/index.html)

+ 2009-TOG - A Benchmark for 3D Mesh Segmentation. [[Paper]](https://segeval.cs.princeton.edu/public/paper.pdf)[[Dataset]](https://segeval.cs.princeton.edu/)

+ 2010-TOG - Learning 3D Mesh Segmentation and Labeling. [[Paper]](https://people.cs.umass.edu/~kalo/papers/LabelMeshes/LabelMeshes.pdf)[[Dataset]](https://people.cs.umass.edu/~kalo/papers/LabelMeshes/)

+ 2012-TOG - Active Co-Analysis of a Set of Shapes. [[Paper]](http://irc.cs.sdu.edu.cn/~yunhai/public_html/ssl/ssl.pdf)[[Dataset]](http://irc.cs.sdu.edu.cn/~yunhai/public_html/ssl/ssd.htm)[[Project Page]](http://irc.cs.sdu.edu.cn/~yunhai/public_html/ssl/ssl.htm)

+ 2013-TOG - Projective Analysis for 3D Shape Segmentation. [[Paper]](http://irc.cs.sdu.edu.cn/~yunhai/public_html/psa.html)[[Dataset]](http://irc.cs.sdu.edu.cn/~yunhai/public_html/psa/psad.html)

+ 2016-TOG - Point labels on ShapeNet Data - A Scalable Active Framework for Region Annotation in 3D Shape Collections. [[Paper]](http://cs.stanford.edu/~ericyi/papers/part_annotation_16.pdf)[[Dataset]](https://cs.stanford.edu/~ericyi/project_page/part_annotation/)

+ 2017-SIGGRAPH - Learning Hierarchical Shape Segmentation and Labeling from Online Repositories. [[Paper]](https://arxiv.org/abs/1705.01661)[[Dataset]](https://cs.stanford.edu/~ericyi/project_page/hier_seg/index.html)

+ 2017-CVPR - Mesh labels on ShapeNet Data - 3D Shape Segmentation with Projective Convolutional Networks. [[Paper]](https://people.cs.umass.edu/~kalo/papers/shapepfcn/ShapePFCN.pdf)[[Dataset]](https://people.cs.umass.edu/~kalo/papers/shapepfcn/index.html)[[Code]](https://github.com/kalov/ShapePFCN)

+ 2018-SIGGRAPH-Asia - Learning to Group and Label Fine-Grained Shape Components. [[Paper]](https://arxiv.org/abs/1809.05050)[[Code & Dataset]](https://kevinkaixu.net/projects/fglabel.html)

+ 2019-CVPR - PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. [[Paper]](https://arxiv.org/abs/1812.02713)[[Dataset]](https://github.com/daerduoCarey/partnet_dataset)

+ 2019-CVPR - PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation. [[Paper]](https://arxiv.org/abs/1903.00709)[[Dataset]](https://github.com/kevin-kaixu/partnet-symh)[[Code]](https://github.com/FENGGENYU/PartNet)

***Classification Labels***

+ 2004 - The princeton shape benchmark. [[Paper]](https://shape.cs.princeton.edu/benchmark/benchmark.pdf)[[Dataset]](https://shape.cs.princeton.edu/benchmark/)

+ 2015-CVPR - ModelNet, 3D ShapeNets: A Deep Representation for Volumetric Shapes. [[Paper]](http://3dvision.princeton.edu/projects/2014/3DShapeNets/paper.pdf)[[Dataset]](http://modelnet.cs.princeton.edu/#)

**Merics**

+ Earth Mover Distance (EMD) - [[Sparse]](https://github.com/daerduoCarey/PyTorchEMD)[[Dense]](https://github.com/Colin97/MSN-Point-Cloud-Completion/tree/master/emd)

+ Chamfer Distance (CD) - [[Code]](https://github.com/facebookresearch/DeepSDF/blob/master/deep_sdf/metrics/chamfer.py)

+ Shell-IoU, f-score - [[Code]](https://github.com/cvlab-epfl/UCLID-Net/blob/c3464ab799544657c4feb169fe2b082668124579/utils.py#L94)

**Other Resources**

+ [awesome point cloud analysis](https://github.com/Yochengliu/awesome-point-cloud-analysis)