Abstract | ||
---|---|---|
In this work, we revise the problem of human body shape estimation from monocular imagery. Starting from a statistical human shape model that describes a body shape with shape parameters, we describe a novel approach to automatically estimate these parameters from a single input shape silhouette using semi-supervised learning. By utilizing silhouette features that encode local and global properties robust to noise, pose and view changes, and projecting them to lower dimensional spaces obtained through multi-view learning with canonical correlation analysis, we show how regression forests can be used to compute an accurate mapping from the silhouette to the shape parameter space. This results in a very fast, robust and automatic system under mild self-occlusion assumptions. We extensively evaluate our method on thousands of synthetic and real data and compare it to the state-of-art approaches that operate under more restrictive assumptions. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46493-0_6 | COMPUTER VISION - ECCV 2016, PT IV |
Keywords | Field | DocType |
Body Shape,Canonical Correlation Analysis,Shape Estimation,Kernel Canonical Correlation Analysis,Template Mesh | Computer vision,ENCODE,Kernel canonical correlation analysis,Pattern recognition,Regression,Silhouette,Computer science,Canonical correlation,Artificial intelligence,Shape parameter,Monocular | Conference |
Volume | ISSN | Citations |
9908 | 0302-9743 | 14 |
PageRank | References | Authors |
0.57 | 41 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Endri Dibra | 1 | 34 | 2.52 |
A. C. Öztireli | 2 | 183 | 12.94 |
Remo Ziegler | 3 | 361 | 21.58 |
Markus H. Gross | 4 | 10154 | 549.95 |