Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
Parting with Illusions about Deep Active Learning
Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
What Do Single-view 3D Reconstruction Networks Learn?
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
Learning to Generate Chairs, Tables and Cars with Convolutional Networks
Multi-view 3D Models from Single Images with a Convolutional Network