Overview

Deep learning is proven to be a powerful tool to build models for language (one-dimensional) and image (two-dimensional) understanding. Tremendous efforts have been devoted to these areas, however, it is still at the early stage to apply deep learning to 3D data, despite their great research values and broad real-world applications. In particular, existing methods poorly serve the three-dimensional data that drives a broad range of critical applications such as augmented reality, autonomous driving, graphics, robotics, medical imaging, neuroscience, and scientific simulations. These problems have drawn the attention of researchers in different fields such as neuroscience, computer vision, and graphics.

The goal of this workshop is to foster interdisciplinary communication of researchers working on 3D data (Computer Vision and Computer Graphics) so that more attention of broader community can be drawn to 3D deep learning problems. Through those studies, new ideas and discoveries are expected to emerge, which can inspire advances in related fields.

This workshop is composed of invited talks, oral presentations of outstanding submissions and a poster session to showcase the state-of-the-art results on the topic. In particular, a panel discussion among leading researchers in the field is planned, so as to provide a common playground for inspiring discussions and stimulating debates.

The workshop will be held on Dec 9 at NIPS 2016 in Barcelona, Spain.

Speakers

Schedule

Dec 9, 2016 at Room 115

TimeSpeakerSlidesTopic
08:30 - 08:45Fisher YuWelcome
08:45 - 09:15Thomas BroxPDFLearning 3D representations, disparity estimation, and structure from motion
09:15 - 09:45Thomas FunkhouserPDFScene Understanding with 3D Deep Networks
09:45 - 10:30Coffee Break
10:30 - 11:00Hao SuPDF3D object reconstruction and abstraction by deep learning
11:00 - 11:30Jiajun WuPDFLearning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
11:30 - 12:00Reza ZadehPDFFusionNet: 3D Object Classification Using Multiple Data Representations
12:00 - 14:30Lunch & Poster session
14:30 - 15:00Michael BronsteinPDFLearning deformable 3D correspondence with intrinsic convolutional neural networks
15:00 - 15:30Andrew BrockPPTGenerative and Discriminative Voxel Modeling with Convolutional Neural Networks
15:30 - 16:00Coffee break
16:00 - 16:30Abhinav GuptaKEYRepresenting 3D: From Surface Normals to Voxels
16:30 - 17:00Alexandr NotchenkoPDFSparse 3D Convolutional Neural Networks for Large-Scale Shape Retrieval
17:00 - 17:30Jianxiong XiaoPanel Discussion
17:30 - 17:45Closing

Abstracts

Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman and Joshua Tenenbaum
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
Abstract - Poster - Webpage - Code

Charlie Nash and Chris Williams
Generative models of part-structured 3D objects
Abstract - Poster

Taylor Dahlke, Mauricio Araya-Polo, Chiyuan Zhang and Charlie Frogner
Predicting geological features in 3D Seismic Data
Abstract - Poster

Akshay Rangamani, Tao Xiong, Arun A Nair, Trac Tran and Sang Chin
Landmark Detection and Tracking in Ultrasound using a CNN-RNN Framework

Organizers