Theme

3D vision has made tremendous progress in the past ten years. Autonomous cars with LIDARs collect petabytes of 3D data, and depth sensors and repositories like Shapenet provide the millions of instances required by large-scale learning systems. At the same time, a wide variety of classic 3D vision problems, ranging from 3D estimation from still images to 3D model retrieval have seen dramatic performance gains, enabling new capabilities.

Unfortunately, despite this progress, there is a fundamental disconnect between most 3D vision and the rest of machine intelligence. In computer vision, 3D papers typically focus on 3D for its own sake, and non-3D papers ignore the underlying 3D structure of the world. Outside of vision, there are even larger disconnects.

The goal of this workshop is to help bridge this gap. We want to examine how 3D vision can help and be helped by other areas of machine intelligence. Our goal is to highlight work that tries to join 3D vision and other disciplines, bring together experts in multiple domains, and to encourage discussion of how to connect with 3D vision. We are particularly interested in work that joins 3D vision with robotics, graphics, cognition, NLP, virtual reality, and semantics.


Speakers

 

Thomas Funkhouser

Ira Kemelmacher-Shlizerman

Leonidas Guibas

Princeton
University of Washington
Stanford
 

Kostas Daniilidis

Jitendra Malik

Jana Kosecka

Dieter Fox

University of Pennsylvania
University of California, Berkeley
George Mason University
University of Washington

Schedule

9:20-9:30Welcome and Overview
9:30-10:00 Leonidas Guibas
10:00-10:30 Ira Kemelmacher-Shlizerman
10:30-11:00Coffee Break
11:00-11:30 Jitendra Malik
11:30-12:00 Dieter Fox
12:00-2:00Lunch
2:00-2:30 Jana Kosecka
2:30-3:00 Kostas Daniilidis
3:00-3:05 Special announcement from Frank Dellaert (Facebook) about SUMO (Scene Understanding and Modeling) Challenge
3:00-4:30 Poster Session (Hall 1, Boards F1-20) and Coffee Break
4:30-5:00 Tom Funkhouser
5:00-5:30Panel Discussion

Invited Posters

We're excited to have a mix of papers from CVPR 2018, ICCV 2017, as well as work from other non-CVPR/ICCV/ECCV conferences. Our aim is to get people with diverse perspective on 3D in the same room and talking about both problems and tools for solving them.

6-dof Object Pose from Semantic Keypoints
G. Pavlakos, X. Zhou, A. Chan, K. G. Derpanis, K. Daniilidis
ICRA 2017

Adversarial Inverse Graphics Networks: Learning 2D-To-3D Lifting and Image-To-Image Translation From Unpaired Supervision
H. F. Tung, A. W. Harley, W. Seto, K. Fragkiadaki
ICCV 2017

CSGNet: Neural Shape Parser for Constructive Solid Geometry
G. Sharma, R. Goyal, D. Liu, E. Kalogerakis, S. Maji
CVPR 2018

Deep Marching Cubes: Learning Explicit Surface Representations
Y. Liao, S. Donne, A. Geiger
CVPR 2018

End-to-end Recovery of Human Shape and Pose
A. Kanazawa, M. Black, D. Jacobs, J. Malik
CVPR 2018

Grass: Generative Recursive Autoencoders for Shape Structures
J. Li, K. Xu, S. Chaudhuri, E. Yumer, H. Zhang, L. Guibas
SIGGRAPH 2017

IQA: Visual Question Answering in Interactive Environments
D. Gordon, A. Kembhavi, M. Rastegari, J. Redmon, D. Fox, A. Farhadi
CVPR 2018

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
L. Landrieu and M. Simonovsky
CVPR 2018

Learning 3D Object Categories by Looking Around Them
D. Novotny, D. Larlus, A. Vedaldi
ICCV 2017

Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations
X. Yan, J. Hsu, M. Khansari, Y. Bai, A. Pathak, A. Gupta, J. Davidson, H. Lee
ICRA 2018

Learning Task-Oriented Grasping for Tool Manipulation with Simulated Self-Supervision
K. Fang, Y. Zhu, A. Garg, V. Mehta, A. Kuryenkov, L. Fei-Fei, S. Savarese
RSS 2018

MapNet: An Allocentric Spatial Memory for Mapping Environments
J. Henriques and A. Vedaldi
CVPR 2018

MegaDepth: Learning Single-View Depth Prediction from Internet Photos
Z. Li and N. Snavely
CVPR 2018

Neural 3D Mesh Renderer
H. Kato, Y. Ushiku, T. Harada
CVPR 2018

Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image
R. Zhu, H. K. Galoogahi, C. Wang, S. Lucey
ICCV 2017

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
X. Sun*, J. Wu*, X. Zhang, Z. Zhang, C. Zhang, T. Xue, J. B. Tenenbaum, W. T. Freeman
CVPR 2018

PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
C. Liu, J. Yang, D. Ceylan, E. Yumer, Y. Furukawa
CVPR 2018

Surface Normals in the Wild
W. Chen, D. Xiang, J. Deng
ICCV 2017

Tangent Convolutions for Dense Prediction in 3D
M. Tatarchenko, J. Park, V. Koltun, Q. Zhou
CVPR 2018

People

 
Organizers
 

David Fouhey

Qixing Huang

Joseph Lim

University of California, Berkeley
University of Texas at Austin
University of Southern California
 

Hao Su

Shubham Tulsiani

University of California, San Diego
University of California, Berkeley
 
Senior Organizers
 

Jitendra Malik

David Forsyth

University of California, Berkeley
University of Illinois, Urbana-Champaign

Contact Info

E-mail: {dfouhey,shubhtuls} at eecs dot berkeley dot edu