The Vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 103-110
Abstract
Fitting an articulated model to image data is often approached as an optimization over both model pose and model-to-image correspondence. For complex models such as humans, previous work has required a good initialization, or an alternating minimization between correspondence and pose. In this paper we investigate one-shot pose estimation: can we directly infer correspondences using a regression function trained to be invariant to body size and shape, and then optimize the model pose just once? We evaluate on several challenging single-frame data sets containing a wide variety of body poses, shapes, torso rotations, and image cropping. Our experiments demonstrate that one-shot pose estimation achieves state of the art results and runs in real-time.Keywords
This publication has 19 references indexed in Scilit:
- Efficient regression of general-activity human poses from depth images2011
- Real-time human pose recognition in parts from single depth images2011
- Efficient and Robust Shape Matching for Model Based Human Motion Capture2011
- Gradient Flows for Optimizing Triangular Mesh-based Surfaces: Applications to 3D Reconstruction Problems Dealing with VisibilityInternational Journal of Computer Vision, 2010
- Real time motion capture using a single time-of-flight camera2010
- Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction2010
- Optimization and Filtering for Human Motion CaptureInternational Journal of Computer Vision, 2008
- Randomized Trees for Real-Time Keypoint Recognition2005
- Articulated Body Motion Capture by Stochastic SearchInternational Journal of Computer Vision, 2005
- A solution for the best rotation to relate two sets of vectorsActa Crystallographica Section A, 1976