in conjunction with CVPR 2018, Salt Lake City, June 18th 2018.

Topic
This workshop aims at gathering researchers who work on 3D understanding of humans from visual data, including topics such as 3D human pose estimation and tracking, 3D human shape estimation from RGB images or human activity recognition from 3D skeletal data. Current computer vision algorithms and deep learning-based methods can detect people in images and estimate their 2D pose with a remarkable accuracy. However, understanding humans and estimating their pose and shape in 3D is still an open problem. The ambiguities in lifting 2D pose to 3D, the lack of annotated data to train 3D pose regressors in the wild and the absence of a reliable evaluation dataset in real world situations make the problem very challenging. The workshop will include 8 invited talks and 2 poster sessions with a total of 21 posters.

Organizers

                   
Grégory Rogez (Inria), Javier Romero (Amazon)

Sponsors
 

Program

• 09:00 – 08:50 introduction/opening remarks
• 09:00 – 09:30  Dr Christian Wolf (INSA): “Pose or attention for human activity recognition?”
  
• 09:30 – 10:00 Dr Gerard Pons-Moll (MPII): “From pixels to 3D human pose, shape and clothing”
• 10:00 – 11:00 Coffee break / poster session 1
• 11:00 – 11:30 Prof Deva Ramanan (CMU): “Analyzing human poses, tracks, and actions”
• 11:30 – 12:00 Prof Yaser Sheikh (CMU/Facebook): “Social perception: enabling machines to perceive social behavior”
  
• 12:00 – 13:30 Lunch break
• 13:30 – 14:00 Prof Michael J. Black (MPI-IS)
• 14:00 – 14:30 Prof Kostas Daniilidis (UPenn): “3D human pose in-the-wild with diverse supervision”
  
• 14:30 – 15:00 Dr Cordelia Schmid (Inria/Google): “Inference of 3D human body poses and shapes”
  
• 15:00 – 15:30 Prof Iasonas Kokkinos (UCL/Facebook): “DensePose: dense pose estimation in the wild”
  
• 15:30 – 16:30 Coffee break / poster session 2
• 16:30 – 17:00 panel discussion, awards and closing

Speakers

  

Poster session 1:

• 1: Monocular RGB Hand Pose Inference from Unsupervised Refinable Nets
  Endri Dibra; Thomas Wolf; Markus Gross; Cengiz Oztireli; Silvan Melchior; Ali Balkis
• 2: Unsupervised Features for Facial Expression Intensity Estimation over Time
  Joern Ostermann; Maren Awiszus; Stella Graßhof; Felix Kuhnke
• 3: Deep Learning Whole Body Point Cloud Scans from a Single Depth Map
  John Zelek; Nolan Lunscher
• 4: HandyNet: A One-stop Solution to Detect, Segment, Localize & Analyze Driver Hands
  Mohan Trivedi; Akshay Rangesh
• 5: Cross-modal Deep Variational Hand Pose Estimation
  Adrian Spurr, Jie Song, Seonwook Park, Otmar Hilliges.
• 6: 4D Human Body Correspondences from Panoramic Depth Maps.
  Zhong Li, Minye Wu, Yitengwang Zhou, Jingyi Yu
• 7: DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor
  Tao Yu, Zerong Zheng, Kaiwen Guo, Jianhui Zhao, Qionghai Dai, Hao Li, Gerard Pons-Moll and Yebin Liu.
• 8: 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning
  Diogo C. Luvizon, David Picard, Hedi Tabia
• 9: Ordinal Depth Supervision for 3D Human Pose Estimation
  Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis
• 10: First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
  Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek, Tae-Kyun Kim

Poster session 2:

• 11: Hand Pose Estimation via Latent 2.5D Heatmap Regression
  Umar Iqbal, Pavlo Molchanov, Thomas Breuel, Juergen Gall, Jan Kautz
• 12: A generalizable approach for multi-view 3D human pose regression and the release of the MVOR dataset
  Abdolrahim Kadkhodamohammadi, Nicolas Padoy
• 13: End-to-end Recovery of Human Shape and Pose
  Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra Malik
• 14: Learning Monocular 3D Human Pose Estimation from Multi–view Images
  Helge Rhodin, Jörg Spörri, Isinsu Katircioglu, Victor Constantin,
  Frédéric Meyer, Erich Müller, Mathieu Salzmann and Pascal Fua
• 15: FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
  Nitika Verma ; Edmond Boyer ; Jakob Verbeek.
• 16: Extreme 3D Face Reconstruction: Seeing Through Occlusions
  Anh Tuấn Trần ; Tal Hassner ; Iacopo Masi ; Eran Paz ; Yuval Nirkin ; Gérard Medioni.
• 17: Video Based Reconstruction of 3D People Models
  Thiemo Alldieck ; Marcus Magnor ; Weipeng Xu ; Christian Theobalt ; Gerard Pons-Moll
• 18: Coding Kendall’s Shape Trajectories for 3D Action Recognition.
  Amor BEN TANFOUS, Hassen DRIRA, Boulbaba BEN AMOR
• 19: Learning Pose Specific Representations by Predicting Different Views
  Georg Poier, David Schinagl and Horst Bischof
• 20: GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
  Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt.
• 21: Learning to Estimate 3D Human Pose and Shape from a Single Color Image
  Georgios Pavlakos, Luyang Zhu, Xiaowei Zhou, Kostas Daniilidis