- 3D Point-Capsule Networks
- Visual Object Networks: Image Generation with Disentangled 3D Representation
- Deep Geometric Prior for Surface Reconstruction
- Robustness of 3D Deep Learning in an Adversarial Setting
- Disentangled Representation Learning for 3D Face Shape
- DeepCaps: Going Deeper with Capsule Networks
- PointGrid: A Deep Network for 3D Shape Understanding
- 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
- Learning Descriptor Networks for 3D Shape Synthesis and Analysis
- Variational Autoencoders for Deforming 3D Mesh Models
- Im2Struct: Recovering 3D Shape Structure from a Single RGB Image
- Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
- Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
- Recurrent Slice Networks for 3D Segmentation of Point Clouds
- LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
- Triplet-Center Loss for Multi-View 3D Object Retrieval
- Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
- A Papier-Mach ˆ e Approach to Learning 3D Surface Generation
- FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans
- Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization
- Learning Priors for Semantic 3D Reconstruction
- GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
- Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
- Recovering 3D Planes from a Single Image via Convolutional Neural Networks
- Simultaneous 3D Reconstruction for Water Surface and Underwater Scene
- Learning Shape Priors for Single-View 3D Completion and Reconstruction
- PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction
- 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
- Learning to Reconstruct High-quality 3D Shapes with Cascaded Fully Convolutional Networks
- 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation
- Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
- Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images