Learning-based Reconstruction, Modeling, Shape Representation, and Processing

Shape generation

• Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses
• BSP Net

Deep learning for classification and segmentation

• PointNet

Shape representation

• Overfit Neural Networks as a Compact Shape Representation
• DeepSDF: Learning Continuous Signed Distance Functions

Reconstruction from point clouds

• Points2Surf Learning Implicit Surfaces from Point Clouds
• Point2Mesh
• Learning Deformable Tetrahedral Meshes for 3D Reconstruction
• PC2WF: 3D WIREFRAME RECONSTRUCTION FROM RAW POINT CLOUDS

Reconstruction from images

• Automatic 3D building reconstruction from multi-view aerial images with deep learning.
• Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
• PatchmatchNet: Learned Multi-View Patchmatch Stereo
• Surfacenet: An end-to-end 3d neural network for multiview stereopsis.
• BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
• Vision Transformers for Dense Prediction
• Multi-view 3D Reconstruction with Transformer
• DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
• M3VSNet: Unsupervised Multi-metric Multi-view Stereo Network
• TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
• Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

Style transfer

• Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
• FrankenGAN: Guided Detail Synthesis for Building Mass Models using Style-Synchonized GANs

Plane detection networks

• Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
• PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
• PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

Stereo Matching

• Pyramid Stereo Matching Network
• Group-wise Correlation Stereo Network
• EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching
• SMD-Nets: Stereo Mixture Density Networks