ABSTRACT
Deep learning has recently gained popularity achieving state-of-the-art performance in tasks involving text, sound, or image processing. Due to its outstanding performance, there have been efforts to apply it in more challenging scenarios, for example, 3D data processing. In this talk, I will give an overview of the progress in 3D deep learning based upon my own work, covering a broad range of topics including 3D recognition, 3D reconstruction from single images, novel-view synthesis, 3D shape space learning, 3D shape completion, etc. Based upon the overview of the current progress, I will also project a few possible directions to push the field forward, by putting it in the perspective of generic AI.