Abstract | ||
---|---|---|
Given a template image with known 3D structure, we show how to refine the rough reconstruction of nonrigid surfaces from existing feature-based methods through efficient direct image alignment. Under the mild assumption that the barycentric coordinates of each 3D point on the surface keep constant, we prove that the template and the input image are correlated by piecewise homography, based on which a direct Lucas-Kanade image alignment method is proposed to iteratively recover an inextensible surface even with poor texture and sharp creases. To accelerate the direct Lucas-Kanade method, an equivalent but much more efficient method is proposed as well, in which the most time-consuming part of the Hessian can be pre-computed as a result of combining additive and inverse compositional expressions. Sufficient experiments on both synthetic and real images demonstrate the accuracy and efficiency of our proposed methods. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-19282-1_7 | ACCV (4) |
Keywords | Field | DocType |
efficient image alignment,template image,direct lucas-kanade image alignment,direct lucas-kanade method,real image,input image,structure refinement,feature-based method,efficient method,efficient direct image alignment,inextensible surface,nonrigid surface,lucas kanade | Inverse,Computer vision,Image alignment,Expression (mathematics),Computer science,Barycentric coordinates,Hessian matrix,Homography,Artificial intelligence,Real image,Piecewise | Conference |
Volume | ISSN | Citations |
6495 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 20 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yinqiang Zheng | 1 | 158 | 25.35 |
shigeki sugimoto | 2 | 115 | 11.82 |
Masatoshi Okutomi | 3 | 869 | 103.67 |