Abstract | ||
---|---|---|
We present a generative model based method for recovering both the shape and the reflectance of the surface(s) of a scene from multiple images, assuming that illumination conditions are known in advance. Based on a variational framework and via gradient descents, the algorithm minimizes simultaneously and consistently a global cost functional with respect to both shape and reflectance. Contrary to previous works which consider specific individual scenarios, our method applies to a number of scenarios --- mutiview stereovision, multiview photometric stereo, and multiview shape from shading. In addition, our approach naturally combines stereo, silhouette and shading cues in a single framework and, unlike most previous methods dealing with only Lambertian surfaces, the proposed method considers general dichromatic surfaces. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-02256-2_62 | SSVM |
Keywords | Field | DocType |
algorithm minimizes,multiview shape,generic scene recovery,single framework,shading cue,lambertian surface,previous method,multiple images,variational framework,previous work,multiview photometric stereo,shape from shading,cost function,gradient descent,photometric stereo | Computer vision,Gradient descent,Silhouette,Artificial intelligence,Reflectivity,Mathematics,Photometric stereo,Generative model,Shading | Conference |
Volume | ISSN | Citations |
5567 | 0302-9743 | 2 |
PageRank | References | Authors |
0.39 | 23 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kuk-Jin Yoon | 1 | 1089 | 67.76 |
Emmanuel Prados | 2 | 450 | 20.47 |
Peter Sturm | 3 | 2696 | 206.38 |