A benchmark for best view selection of 3D objects

The best view selection corresponds to the task of automatically selecting the most representative view of a 3D model. In this paper, we describe a benchmark for evaluation of best view selection algorithms. The benchmark consists of the preferred views of 68 3D models provided by 26 human subjects. The data was collected using a web-based subjective experiment where the users were asked to select the most informative view of a 3D model. We provided a quantitative evaluation measure based on this ground truth data, and compared the performances of seven best view selection algorithms.

[1]  Mateu Sbert,et al.  Automatic View Selection Using Viewpoint Entropy and its Application to Image‐Based Modelling , 2003, Comput. Graph. Forum.

[2]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[3]  Daniel Cohen-Or,et al.  Upright orientation of man-made objects , 2008, ACM Trans. Graph..

[4]  A. David Marshall,et al.  Viewpoint Selection for Complete Surface Coverage of Three Dimensional Objects , 1998, BMVC.

[5]  Jean-Philippe Vandeborre,et al.  3D-model view characterization using equilibrium planes , 2008 .

[6]  Hamid Laga.  Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes , 2010, 3DOR@Eurographics.

[7]  Silvia Biasotti,et al.  What’s in an image? , 2005, The Visual Computer.

[8]  Mateu Sbert,et al.  Viewpoint Selection using Viewpoint Entropy , 2001, VMV.

[9]  S. Edelman,et al.  Canonical views in object representation and recognition , 1994, Vision Research.

[10]  Michael J Tarr,et al.  What defines a view? , 2001, Vision Research.

[11]  Hans-Peter Seidel,et al.  Towards Stable and Salient Multi-View Representation of 3D Shapes , 2006, IEEE International Conference on Shape Modeling and Applications 2006 (SMI'06).

[12]  M J Tarr,et al.  What Object Attributes Determine Canonical Views? , 1999, Perception.

[13]  Mongi A. Abidi,et al.  Shape analysis algorithm based on information theory , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[14]  Michela Spagnuolo,et al.  Semantics-driven best view of 3D shapes , 2009, Comput. Graph..

[15]  William C. Regli,et al.  Geometric reasoning via internet CrowdSourcing , 2009, Symposium on Solid and Physical Modeling.

[16]  David W. Jacobs,et al.  Mesh saliency , 2005, ACM Trans. Graph..