Technical Section: Estimating body shape of dressed humans
Computers and Graphics
Parametric reshaping of human bodies in images
ACM SIGGRAPH 2010 papers
Video-based reconstruction of animatable human characters
ACM SIGGRAPH Asia 2010 papers
Robust Pose Recognition of the Obscured Human Body
International Journal of Computer Vision
A 2D human body model dressed in eigen clothing
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Reference consistent reconstruction of 3D cloth surface
Computer Vision and Image Understanding
3D Human model adaptation by frame selection and shape-texture optimization
Computer Vision and Image Understanding
A Self-Training Approach for Visual Tracking and Recognition of Complex Human Activity Patterns
International Journal of Computer Vision
Clothed and naked human shapes estimation from a single image
CVM'12 Proceedings of the First international conference on Computational Visual Media
Deformable model for estimating clothed and naked human shapes from a single image
The Visual Computer: International Journal of Computer Graphics
Special Section on CAD/Graphics 2013: SCAPE-based human performance reconstruction
Computers and Graphics
Hi-index | 0.00 |
We propose a method to estimate the detailed 3D shape of a person from images of that person wearing clothing. The approach exploits a model of human body shapes that is learned from a database of over 2000 range scans. We show that the parameters of this shape model can be recovered independently of body pose. We further propose a generalization of the visual hull to account for the fact that observed silhouettes of clothed people do not provide a tight bound on the true 3D shape. With clothed subjects, different poses provide different constraints on the possible underlying 3D body shape. We consequently combine constraints across pose to more accurately estimate 3D body shape in the presence of occluding clothing. Finally we use the recovered 3D shape to estimate the gender of subjects and then employ gender-specific body models to refine our shape estimates. Results on a novel database of thousands of images of clothed and "naked" subjects, as well as sequences from the HumanEva dataset, suggest the method may be accurate enough for biometric shape analysis in video.