Learning from Synthetic Humans

Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.

[1]  David Sweeney,et al.  Learning to be a depth camera for close-range human capture and interaction , 2014, ACM Trans. Graph..

[2]  Ben Taskar,et al.  MODEC: Multimodal Decomposable Models for Human Pose Estimation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Sudeep Sarkar,et al.  Learning Camera Viewpoint Using CNN to Improve 3D Body Pose Estimation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[4]  Leonidas J. Guibas,et al.  Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Bernt Schiele,et al.  Learning people detection models from few training samples , 2011, CVPR 2011.

[6]  Yinda Zhang,et al.  LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop , 2015, ArXiv.

[7]  Varun Ramakrishna,et al.  Convolutional Pose Machines , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[9]  Kate Saenko,et al.  Learning Deep Object Detectors from 3D Models , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Stefano Soatto,et al.  Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images , 2008, ECCV.

[11]  David Vázquez,et al.  Learning appearance in virtual scenarios for pedestrian detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Cristian Sminchisescu,et al.  Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Thomas Brox,et al.  FlowNet: Learning Optical Flow with Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Michael J. Black,et al.  FlowCap: 2D Human Pose from Optical Flow , 2015, GCPR.

[15]  Yi Yang,et al.  Attention to Scale: Scale-Aware Semantic Image Segmentation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Xiaowei Zhou,et al.  Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Bernt Schiele,et al.  2D Human Pose Estimation: New Benchmark and State of the Art Analysis , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[19]  Cristian Sminchisescu,et al.  Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Cristian Sminchisescu,et al.  Latent structured models for human pose estimation , 2011, 2011 International Conference on Computer Vision.

[21]  Rob Fergus,et al.  Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[22]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[23]  Bernt Schiele,et al.  Articulated people detection and pose estimation: Reshaping the future , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Juergen Gall,et al.  A Dual-Source Approach for 3D Pose Estimation from a Single Image , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Michael J. Black,et al.  MoSh: motion and shape capture from sparse markers , 2014, ACM Trans. Graph..

[26]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[27]  Michael J. Black,et al.  SMPL: A Skinned Multi-Person Linear Model , 2015, ACM Trans. Graph..

[28]  Weifeng Chen,et al.  Single-Image Depth Perception in the Wild , 2016, NIPS.

[29]  Weichao Qiu.  Generating Human Images and Ground Truth using Computer Graphics , 2016 .

[30]  Kathleen M. Robinette,et al.  Civilian American and European Surface Anthropometry Resource (CAESAR), Final Report. Volume 1. Summary , 2002 .

[31]  Ajmal S. Mian,et al.  Learning a non-linear knowledge transfer model for cross-view action recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Hans-Peter Seidel,et al.  EgoCap , 2016, ACM Trans. Graph..

[33]  Qiao Wang,et al.  VirtualWorlds as Proxy for Multi-object Tracking Analysis , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Cordelia Schmid,et al.  MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild , 2016, NIPS.

[35]  Robin Green,et al.  Spherical Harmonic Lighting: The Gritty Details , 2003 .

[36]  Guosheng Lin,et al.  Deep convolutional neural fields for depth estimation from a single image , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Ajmal Mian,et al.  3D Action Recognition from Novel Viewpoints , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Zhenhua Wang,et al.  Synthesizing Training Images for Boosting Human 3D Pose Estimation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[39]  Wolfram Burgard,et al.  Deep learning for human part discovery in images , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[40]  Mohan S. Kankanhalli,et al.  Marker-Less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps , 2016, ECCV.

[41]  Cristian Sminchisescu,et al.  Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[42]  Michael J. Black,et al.  Dyna: a model of dynamic human shape in motion , 2015, ACM Trans. Graph..