Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks

no code implementations • CVPR 2017 • Amir Arsalan Soltani, Haibin Huang, Jiajun Wu, Tejas D. Kulkarni, Joshua B. Tenenbaum

We take an alternative approach: learning a generative model over multi-view depth maps or their corresponding silhouettes, and using a deterministic rendering function to produce 3D shapes from these images.

A Greedy, Flexible Algorithm to Learn an Optimal Bayesian Network Structure

no code implementations • 24 Nov 2014 • Amir Arsalan Soltani

Our algorithm runs in a much less time than the previously known methods and guarantees to have an optimality of close to 99%.