Generic Scene Recovery using Multiple Images

Kuk-Jin Yoon (1) , Emmanuel Prados (1) , Peter Sturm (1)

1 PERCEPTION - Interpretation and Modelling of Images and Videos

In this paper, a generative model based method for recovering both the shape and the reflectance of the surface(s) of a scene from multiple images is presented, 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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Kuk-Jin Yoon, Emmanuel Prados, Peter Sturm. Generic Scene Recovery using Multiple Images. SSVM 2009 - 2nd International Conference on Scale Space and Variational Methods in Computer Vision, Jun 2009, Voss, Norway. pp.745-757, ⟨10.1007/978-3-642-02256-2_62⟩. ⟨inria-00357139⟩