1. Joint 2d-3d-semantic data for indoor scene understanding;Armeni,2017
2. Generative modeling for multi-task visual learning;Bao
3. Large scale gan training for high fidelity natural image synthesis;Brock,2018
4. SE3-nets: Learning rigid body motion using deep neural networks
5. Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos