Salient Region of Textured 3D Model

In this paper, we propose a salient region detection method for textured 3D models. We define the salient region, not only based on geometry properties, such as mean curvature, but also based on texture properties, such as texture color. Feature maps of geometry and texture are combined to form a saliency map for capturing the visually important regions of a textured 3D model. During the feature maps construction, we apply a novel filter window to obtain proper sample vertices and texels from the 3D geometry domain and 2D texture image domain. Given the saliency map, we have developed a model reduction method, which comprises the geometry simplification mechanism and the texture space optimization mechanism. Experimental results show that the salient regions of a model can be well preserved even if the model texture and geometry are simplified heavily.