找一些图的或者新颖的研究
1.3D Graph Neural Networks for RGBD Semantic Segmentation
PyTorch实现
https://openaccess.thecvf.com/content_ICCV_2017/papers/Qi_3D_Graph_Neural_ICCV_2017_paper.pdf
3D Graph Neural Networks for RGBD Semantic Segmentation
2. SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans
https://arxiv.org/pdf/2003.12622.pdf
我们提出了一种从商品RGB-D传感器重建扫描三维环境的基于CAD的轻量级表示的新方法。我们的关键思想是联合优化CAD模型对齐以及扫描场景的布局估计，明确地建模对象到对象和对象到布局之间的相互关系。由于物体排列和场景布局是内在耦合的，我们表明联合处理该问题有助于生成全局一致的场景表示。通过建立几何体之间的紧密对应关系，将对象CAD模型与场景对齐，并引入一种层次式布局预测方法，从几何体的角和边估计布局平面场景。到为此，我们提出了一种消息传递图神经网络来建模对象与布局之间的相互关系，指导场景中全局对象对齐的生成。通过考虑全局场景布局，与最先进的方法相比，我们实现了显著改进的CAD对齐，在SUNCG上的对齐精度从41.83%提高到58.41%，在ScanNet上从50.05%提高到61.24%。由此产生的基于CAD的表示使我们的方法非常适合于内容创建的应用，例如增强现实或虚拟现实。
3.JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
ECCV2020 as a Spotlight paper
手势识别
4. Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
5.Distilling Knowledge from Graph Convolutional Networks
6. TreeGAN
Pytorch1.0
iccv2019
https://github.com/seowok/TreeGAN
https://blog.csdn.net/weixin_43012220/article/details/101516098
7.https://arxiv.org/pdf/2003.03551.pdf
8.CVPR2020: Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion(不一定和图网络相关)
9.Point-GNN
https://github.com/WeijingShi/Point-GNN
10 https://github.com/FuxiCV/3D-Face-GCNs (Tensorflow)
Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks
https://arxiv.org/pdf/2003.05653.pdf
11. 3D Photography using Context-aware Layered Depth Inpainting
https://arxiv.org/abs/2004.04727
CVPR2020
CVPR 2020. Project page: https://shihmengli.github.io/3D-Photo-Inpainting/
Code: https://github.com/vt-vl-lab/3d-photo-inpainting
Demo: https://colab.research.google.com/drive/1706ToQrkIZshRSJSHvZ1RuCiM__YX3Bz
Facebook出品，demo效果经验
输入是RGBD图
12. Mesh Guided One-shot Face Reenactment Using Graph Convolutional Networks（似乎未开源）
https://arxiv.org/pdf/2008.07783.pdf
13. 场景图生成
https://github.com/jwyang/graph-rcnn.pytorch
https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch
14. 自监督学习+图学习
GPT-GNN: Generative Pre-Training of Graph Neural Networks
15. SRNet
Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On
Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks
Learning to Simulate Complex Physics with Graph Networks
-------
Showing 1–14 of 14 results for all: graph shapenet
101.MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
https://arxiv.org/abs/2010.08682
102.Interactive Annotation of 3D Object Geometry using 2D Scribbles
https://arxiv.org/abs/2008.10719
103.Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds
https://arxiv.org/abs/2007.13344
104.Learning to Segment 3D Point Clouds in 2D Image Space
https://arxiv.org/abs/2003.05593
105.STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image
https://arxiv.org/abs/2003.03551
106.Geometry Sharing Network for 3D Point Cloud Classification and Segmentation
https://arxiv.org/abs/1912.10644
107.Unsupervised Multi-Task Feature Learning on Point Clouds
https://arxiv.org/abs/1910.08207
108.Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
https://arxiv.org/abs/1909.09287
109.PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation
https://arxiv.org/abs/1906.03299
110.Mesh R-CNN
https://arxiv.org/abs/1906.02739
111.GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
https://arxiv.org/abs/1905.08705
112.Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
https://arxiv.org/abs/1904.10014
113.GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
https://arxiv.org/abs/1901.11461
114.RGCNN: Regularized Graph CNN for Point Cloud Segmentation
https://arxiv.org/abs/1806.02952
