3D object reconstruction and abstraction by deep learning

Speaker: Hao Su , Stanford

Date: Tuesday, November 29, 2016

Time: 12:00 PM to 1:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: 32-D507

Event Type:

Room Description:

Host:

Contact: Katherine Bouman, klbouman@csail.mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
None

Reminders to: seminars@csail.mit.edu

Reminder Subject: TALK: Hao Su - 3D object reconstruction and abstraction by deep learning

Abstract:

Computational methods for 3D perception from single images have been attracting increasing attention recently. In particular, deep neural networks have shown promising ability to learn the priors for object shapes from emerging large-scale 3D shape databases. The majority of extant works resort to regular representations such as volumetric grids or collection of images; however, these representations obscure the natural invariance and simple manipulation when it comes to geometric transformations and deformations.

In this talk I will introduce my latest progress on generative networks for 3D geometry based on representations that are unorthodox in the deep learning community, focusing on two tasks:
* High-quality point cloud generation. We build a conditional sampler to predict multiple plausible 3D point clouds from a single input image. The shapes predicted by our algorithm demonstrate significantly better global structure compared with those from volumetric CNNs.
* 3D shape abstraction by geometric primitives. We present a framework for abstracting complex shapes by learning to assemble objects using 3D geometric primitives such as cuboids. Experiments have shown that our unsupervised shape abstraction method produces results that are quite consistent with human annotations.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Katherine Bouman Email at Friday, November 25, 2016 at 9:55 AM.