Thanks to visit codestin.com
Credit goes to github.com

Skip to content

xzb030/IMG_Survey

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 

Repository files navigation

What’s the Situation with Intelligent Mesh Generation: A Survey and Perspectives

This repository complements "What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives"[ arxiv ]. To facilitate better access to the relevant literature, we provide links to the 110 articles mentioned in the article by technical categories, as well as the relevant codes for these articles. In addition, we also provide links to commonly used datasets.

Outline

Abstract

Intelligent mesh generation (IMG) is a relatively new field that refers to a kind of method to generate mesh by machine learning. IMG has greatly expanded the generalizability and practicality of mesh generation techniques, bringing many breakthroughs and potential possibilities for mesh generation. Within its short life span, we have seen tremendous advances in this field. However, there is a lack of surveys focusing on IMG methods covering recent works. In this article, we present an overview of the existing IMG methods systematically. Focusing on 110 preliminary studies describing different IMG methods, we conducted a comprehensive analysis and evaluation from the core technique and application scope of the algorithm, agent learning goals, data types, targeting challenges, advantages and limitations. With the aim of literature collection and classification based on content extraction, we provide three different taxonomies from three views of key technique, output mesh unit element, and applicable input data types. Finally, we highlight some promising future research directions and challenges in IMG.

The main classification criteria

Annual distribution of articles of 6 technical types

text

Timeline of main articles

text

Links to articles and code

Deformation-based

Paper Code Source connection map
A self-organizing neural network approach for automatic mesh generation -- IEEE Transactions on Magnetics 1991 --
DeepGarment : 3D Garment Shape Estimation from a Single Image -- Computer Graphics Forum 2017 --
DeepSketch2Face: a deep learning based sketching system for 3D face and caricature modeling code TOG 2017 --
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images code ECCV 2018 image
Generating 3D Faces using Convolutional Mesh Autoencoders code ECCV 2018 --
Multi-Garment Net: Learning to Dress 3D People From Images code ICCV 2019 image
3DN: 3D Deformation Network code CVPR 2019 image
Deep Mesh Reconstruction From Single RGB Images via Topology Modification Networks code ICCV 2019 image
Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation code ICCV 2019 image
HumanMeshNet: Polygonal Mesh Recovery of Humans code ICCVW 2019 --
Mesh R-CNN code ICCV 2019 image
Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation code ICCV 2019 image
BCNet: Learning Body and Cloth Shape from a Single Image code ECCV 2020 image
Pixel2Mesh: 3D Mesh Model Generation via Image Guided Deformation -- TAMPI 2020 image
Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data code MICCAI 2020 image
X-ray2Shape: Reconstruction of 3D Liver Shape from a Single 2D Projection Image -- EMBC 2020 image
3D Shape Reconstruction of Furniture Object from a Single Real Indoor Image -- ICCWAMTIP 2020 image
3D Reconstruction based on GAT from a Single Image -- ICCWAMTIP 2020 image
MeshingNet: A New Mesh Generation Method Based on Deep Learning -- ICCS 2020 --
Back To Meshes: Optimal Simulation-ready Mesh Prototypes For Autoencoder-based 3D Car Point Clouds -- SSCI 2020 --
Surface Hof: Surface Reconstruction From A Single Image Using Higher Order Function Networks -- ICIP 2020 --
Leveraging 2D Data to Learn Textured 3D Mesh Generation code CVPR 2020 --
Mesh Variational Autoencoders With Edge Contraction Pooling code CVPR 2020 --
Point2Mesh: a self-prior for deformable meshes code TOG 2020 image
Neural mesh flow: 3D manifold mesh generation via diffeomorphic flows code NeurlPS 2020 image
Learning Manifold Patch-Based Representations of Man-Made Shapes code ICLR 2020 image
LASR: Learning Articulated Shape Reconstruction From a Monocular Video code CVPR 2021 --
Deep Active Surface Models -- cvpr 2021 image
Learning Local Recurrent Models for Human Mesh Recovery -- 2021 3DV --
Learning non-rigid surface reconstruction from spatia-temporal image patches -- 2021 ICPR --
Deep Hybrid Self-Prior for Full 3D Mesh Generation -- ICCV 2021 image
Mesh generation and optimization from digital rock fractures based on neural style transfer -- JRMGE 2021 --
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces From RGB Images code TAMPI 2021 image
SelfRecon: Self Reconstruction Your Digital Avatar From Monocular Video code CVPR 2022 --
Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes code WACV 2022 image
TopoNet: Topology Learning for 3D Reconstruction of Objects of Arbitrary Genus -- Computer Graphics Forum 2022 image
SAniHead: Sketching Animal-Like 3D Character Heads Using a View-Surface Collaborative Mesh Generative Network -- TVCG 2022 image

Classification-based

Paper Code Source connection map
3D object reconstruction and representation using neural networks -- Graphite 2004 --
An ANN-based element extraction method for automatic mesh generation -- Expert Systems with Applications 2005 --
Deep Marching Cubes: Learning Explicit Surface Representations code CVPR 2018 image
Occupancy Networks: Learning 3D Reconstruction in Function Space code CVPR 2019 image
Learning Implicit Fields for Generative Shape Modeling code CVPR 2019 image
Scan2Mesh: From Unstructured Range Scans to 3D Meshes non-official CVPR 2019 --
Mesh R-CNN code ICCV 2019 image
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes code CVPR 2020 image
Local Implicit Grid Representations for 3D Scenes code CVPR 2020 image
Convolutional Occupancy Networks code ECCV 2020 image
Interactive liquid splash modeling by user sketches -- TOG 2020 --
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance code ECCV 2020 image
POINTS2SURF Learning Implicit Surfaces from Point Clouds code ECCV 2020 image
Learning Deformable Tetrahedral Meshes for 3D Reconstruction code NeurIPS 2020 image
PointTriNet: Learned Triangulation of 3D Point Sets code ECCV 2020 image
REIN: Flexible Mesh Generation From Point Clouds code CVPR 2020 --
TransformerFusion: Monocular RGB Scene Reconstruction using Transformers code NeurlPS 2021 image
Deep Implicit Surface Point Prediction Networks code CVPR 2021 image
NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular Video code CVPR 2021 image
SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks code ICCV 2021 image
Vis2Mesh: Efficient Mesh Reconstruction From Unstructured Point Clouds of Large Scenes With Learned Virtual View Visibility code ICCV 2021 image
Deep Implicit Moving Least-Squares Functions for 3D Reconstruction code CVPR 2021 image
DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction code AAAI 2021 image
NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping code 3DV 2021 image
Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching code TPAMI 2021 --
Scalable Surface Reconstruction with Delaunay-Graph Neural Networks code Computer Graph Forum 2021 image
Neural marching cubes code TOG 2021 image
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces From RGB Images code TAMPI 2021 image
Neural Fields As Learnable Kernels for 3D Reconstruction code CVPR 2022 image
Neural Dual Contouring code TOG 2022 image
POCO: Point Convolution for Surface Reconstruction code CVPR 2022 image

Isosurface-based

Paper Code Source connection map
LS-RBF network based 3D surface reconstruction method -- CCDC 2009 --
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks code 3DV 2017 --
Robust flow-guided neural prediction for sketch-based freeform surface modeling code TOG 2018 --
Deep Marching Cubes: Learning Explicit Surface Representations code CVPR 2018 image
Learning to Reconstruct High-quality 3D Shapes with Cascaded Fully Convolutional Networks -- ECCV 2018 --
Occupancy Networks: Learning 3D Reconstruction in Function Space code CVPR 2019 image
DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction code NIPS 2019 image
Learning Implicit Fields for Generative Shape Modeling code CVPR 2019 image
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation code CVPR 2019 image
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes code CVPR 2020 image
Mobile3DRecon: Real-time Monocular 3D Reconstruction on a Mobile Phone -- TVCG 2020 --
SAL: Sign Agnostic Learning of Shapes From Raw Data code CVPR 2020 image
Meshlet Priors for 3D Mesh Reconstruction code CVPR 2020 image
Local Implicit Grid Representations for 3D Scenes code CVPR 2020 image
Convolutional Occupancy Networks code ECCV 2020 image
Interactive liquid splash modeling by user sketches -- TOG 2020 --
POINTS2SURF Learning Implicit Surfaces from Point Clouds code ECCV 2020 image
SSRNet: Scalable 3D Surface Reconstruction Network -- CVPR 2020 image
Neural Unsigned Distance Fields for Implicit Function Learning code NeurIPS 2020 image
MeshSDF: Differentiable Iso-Surface Extraction code NeurIPS 2020 image
TransformerFusion: Monocular RGB Scene Reconstruction using Transformers code NeurlPS 2021 image
Deep Implicit Surface Point Prediction Networks code CVPR 2021 image
NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular Video code CVPR 2021 image
SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks code ICCV 2021 image
Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis code NerulPS 2021 image
Deep Implicit Moving Least-Squares Functions for 3D Reconstruction code CVPR 2021 image
RetrievalFuse: Neural 3D Scene Reconstruction With a Database code ICCV 2021 image
DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction code AAAI 2021 image
Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations code CVPR 2021 image
Shape As Points: A Differentiable Poisson Solver code NerualPS 2021 image
Deep Parametric Surfaces for 3D Outfit Reconstruction from Single View Image -- FG 2021 --
NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping code 3DV 2021 image
Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching code TPAMI 2021 --
Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces code ICML 2021 image
DI-Fusion: Online Implicit 3D Reconstruction With Deep Priors code CVPR 2021 image
Neural marching cubes code TOG 2021 image
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces From RGB Images code TAMPI 2021 image
Extracting Triangular 3D Models, Materials, and Lighting From Images code CVPR 2022 --
AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation code CVPR 2022 --
Neural Fields As Learnable Kernels for 3D Reconstruction code CVPR 2022 image
Reconstructing Surfaces for Sparse Point Clouds With On-Surface Priors code CVPR 2022 image
Neural Dual Contouring code TOG 2022 --
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM code CVPR 2022 image
Neural RGB-D Surface Reconstruction code CVPR 2022 image

Delaunay-triangulation-based

Paper Code Source connection map
A density driven mesh generator guided by a neural network -- IEEE T MAGN 1993 --
Automatic mesh generation by the let-it-grow neural network -- IEEE T MAGN 1996 --
A finite element mesh generator based on an adaptive neural network -- IEEE T MAGN 1998 --
A neural network generator for tetrahedral meshes -- IEEE T MAGN 2003 --
An Optimized Generator of Finite Element Meshes Based on a Neural Network -- IEEE Transactions on Magnetics 2008 --
Vis2Mesh: Efficient Mesh Reconstruction From Unstructured Point Clouds of Large Scenes With Learned Virtual View Visibility code ICCV 2021 image
Differentiable surface triangulation code TOG 2021 --
Learning Delaunay Surface Elements for Mesh Reconstruction code CVPR 2021 image
Scalable Surface Reconstruction with Delaunay-Graph Neural Networks code Computer Graph Forum 2021 image

Parametrization-based

Paper Code Source connection map
Incomplete Points Cloud Data Surface Reconstruction Based on Neural Network -- IIHMSP 2008 --
An Adaptive Learning Approach for 3-D Surface Reconstruction From Point Clouds -- TNNLS 2008 --
Robust surface reconstruction via dictionary learning -- TOG 2014 --
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks code CVPR 2017 --
A Papier-Mâché Approach to Learning 3D Surface Generation code CVPR 2018 image
Multi-Garment Net: Learning to Dress 3D People From Images code ICCV 2019 image
PGAN: Prediction Generative Adversarial Nets for Meshes -- VCIP 2019 image
Deep Geometric Prior for Surface Reconstruction code CVPR 2019 image
Meshlet Priors for 3D Mesh Reconstruction code CVPR 2020 image
Learning Manifold Patch-Based Representations of Man-Made Shapes code ICLR 2020 image
Differentiable surface triangulation code TOG 2021 --
Deep Hybrid Self-Prior for Full 3D Mesh Generation -- ICCV 2021 image
Learning Delaunay Surface Elements for Mesh Reconstruction code CVPR 2021 image
Learning Direction Fields for Quad Mesh Generation -- Computer Graph Forum 2021 --
Setch2PQ: Freeform Planar Quadrilateral Mesh Design via a Single Sketch -- TVCG 2022 image
MGNet: a novel differential mesh generation method based on unsupervised neural networks -- Engineering with Computers 2022 --
PCGAN: Prediction-Compensation Generative Adversarial Network for Meshes -- TCSVT 2022 image

Advancing-front-based

Paper Code Source connection map
An ANN-based element extraction method for automatic mesh generation -- Expert Systems with Applications 2005 --
A new unstructured hybrid mesh generation method based on BP-ANN -- IPCS 2022 --
Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach -- arXiv:2203.11203 --

Common data set and links

Triangle Mesh

Commonly used: Princeton ModelNet; ShapeNet; TOSCA; COSEG; surface reconstruction benchmark of Berge and Williams; Thingi10K; D-FAUST; Famous; CAD dataset ABC;

Dataset for single image 3D shape modeling: Pix3d;

Facial expression dataset: COMA; MeIn3D;

Human body shapes datasets: MGN; MultiHuman;

Clothed body meshes with real texture: RenderPeople; Axyz; Digit Wardrobe;

Indoor scenes datasets: ScanNet; Scenenet; Matterport3d; Synthetic Rooms;

Quadrilateral mesh

Commonly used :QuadWild;

Clothed body meshes with real texture: RenderPeople;Axyz;

Citation

@ARTICLE{10141677,
  author={Lei, Na and Li, Zezeng and Xu, Zebin and Li, Ying and Gu, Xianfeng},
  journal={IEEE Transactions on Visualization and Computer Graphics}, 
  title={What's the Situation With Intelligent Mesh Generation: A Survey and Perspectives}, 
  year={2023},
  pages={1-20},
  doi={10.1109/TVCG.2023.3281781}}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •