Deep Generative Vision as Approximate Bayesian Computation

By Tejas D. Kulkarni, Ilker Yildirim, Pushmeet Kohli, Winrich Freiwald, Josh Tenenbaum. 2014

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Sergey Levine
2. Yoshua Bengio
3. Abhinav Kumar Gupta
4. Andrew Zisserman
5. Andrea Vedaldi
6. Jitendra Malik
7. Trevor Darrell
8. Yi Yang

Citations in the corpus

• Unsupervised Learning of 3D Structure from Images (2016, methodology): “In our experiments, context is either 1) nothing, 2) an object class label, or 3) one or more views of the scene from different cameras.”
• Training a Feedback Loop for Hand Pose Estimation (2015, background): “Instead, we learn from registered depth images to generate realistic depth images of hands, similar to work on inverse graphics networks [9, 15], and other recent work on generating images [11, 16].”