Estimating Human Shape and Pose from a Single Image Peng Guan Alex Weiss Alexandru Balan Michael J. Black Brown University Department of Computer Science ICCV’ 2009 Body shape and pose from 1 image? Introduction What others do What we do • Estimating 3D human • Estimating both 3D shape pose in uncalibrated and pose in uncalibrated monocular imagery monocular imagery • Use silhouette in multi- camera setting to recover • Use additional monocular cues including smooth 3D body shape shading • Most work assumes the existence of a known • Use GrabCut to produce background to extract foreground region foreground silhouette • In previous body models, • Make height variation height is correlated with concentrated along one other shape variations shape basis vector, which allows “height constrained fitting” Previous Work 3D pose and shape estimation from multiple, calibrated, cameras Balan, A., Sigal, L., Black, M. J., Davis, J., Haussecker, H, “Detailed human shape and pose from images”, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR, Minneapolis, June 2007 SCAPE Body Model D. Anguelov, P. Srinivasan, D. Koller, S. Thrun, J. Rodgers, and J. Davis. SCAPE: Shape completion and animation of people. SIGGRAPH, 24(3):408–416, 2005. Body shape/pose from 1 image: Problems 1. High dimensional body model (shape and pose) – initialization problem. 2. Background unknown 3. Single, monocular image 1. poorly constrained 2. Shape/Pose ambiguities 4. Silhouette insufficient Solution 1: Pose Initialization Better Shape: initialized to mean body shape. Solution 2: Segmentation C. Rother, V. Kolmogorov, and A. Blake. “GrabCut”: Interactive foreground extraction using iterated graph cuts. SIGGRAPH, 23(3):309–314, 2004. Problem: Pose/Shape ambiguities Body shape and pose fitted to a single camera view Solution 3: Height Preserving Shape Space Shape space without height preserving Problem: Silhouette not sufficient Solution 4: Edge Cues Problem: Shape not well constrained Solution 5: Parametric Shape from Shading M. de la Gorce, N. Paragios and David Fleet. Model-Based Hand Tracking with Texture, Shading and Self- occlusions. IEEE Conference in Computer Vision and Pattern Recognition (CVPR), Anchorage 2008. Shading/Overall Cost function Shading cost function: Overall cost function: Experiment: Lab Images Experiment: Lab Images Quantitative Comparison Experiment: Internet Images Experiment: Paintings Conclusions Contributions • Solution to a new problem: Human pose and shape estimation from a single image • Parametric shape from shading for estimating human shape from complex images and paintings • Attribute-constrained body model Limitations • Single point light assumption and simplified model of surface reflection • User assistance for pose initialization • Minimal clothing for shading Acknowledgement • Financial support: NSF IIS-0812364 and the RI Economic Development Corp. • Peng Guan, Alexander Weiss, Alexandru Balan, Michael Black, “Estimating Human Shape and Pose from a Single Image”, Int. Conf. on Computer Vision, ICCV, Kyoto, Japan, Sept. 2009 • Alexander Weiss: GrabCut 3D pose initialization • Alexandru Balan: Height preserving shape space • David Hirshberg: Projection of model edge Thank you!