Most Relevant Viewpoint of an Object: a View-Dependent 3D Saliency Approach

Overview & Synopsis

A viewpoint of a 3D object is the position from which we observe the object. A viewpoint always highlights some 3D parts and discards other parts of an object. Here, we define a good viewpoint as offering a relevant view of the object: a view that best showcases the object and that is the most representative of the object. Best view selection plays an essential role in many computer vision and virtual reality applications. In this paper, given a model and a particular viewpoint, we want to quantify its relevance -not aesthetics. We propose a geometric method for selecting the most relevant viewpoint for a 3D object by combining terms related either to visibility (visible surfaces) or to viewpoint (such as vertex saliency). A main difficulty is to evaluate the quality of an estimated best viewpoint. Thus, we propose an evaluation protocol that considers two different and complementary solutions: a user study with more than 200 participants to collect human preferences and the analysis of image dataset picturing objects of interest. This evaluation highlights the correlation between the proposed method for best view selection and human preferences. Through a quantitative comparison, we show that the proposed approach outperforms the reference methods.