Geometry Meets Deep Learning(專欄)
Geometry Meets Deep Learning
2017
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image
- Visual Attribute Transfer through Deep Image Analogy
- FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
- Inverse Compositional Spatial Transformer Networks
- Convolutional neural network architecture for geometric matching
2016
- Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks
- View Synthesis by Appearance Flow
2015
- FlowNet: Learning Optical Flow with Convolutional Networks
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
- spatial transformer networks
