Texture and Shadow Insensitive Metric for Image-Based Reconstruction

This paper proposes an accurate metric for image based 3d reconstruction without ground truth. Specially, our metric is insensitive to texture changing and shadows, which are commonly occurred in real world scenes. Based on the interreflected rendering model, we improve the accuracy of previous irradiance based metric. Additionally, we estimate the reflectance of each vertex on the surface to support the case with varying reflectance. We also consider the difference between estimated and observed irradiance in our metric to further eliminate the boundary effect of texture changing or self-shadow. Experiments on both indoor and outdoor datasets illustrate the effectiveness of our metric. Our evaluation results are not only more accurate than the results of previous metrics, but also insensitive to the texture and shadow.

[1]  Jan-Michael Frahm,et al.  Next Best View Planning for Active Model Improvement , 2009, BMVC.

[2]  Donald P. Greenberg,et al.  The Irradiance Volume , 1998, IEEE Computer Graphics and Applications.

[3]  J. Arvo.  Analytic methods for simulated light transport , 1995 .

[4]  Pascal Fua,et al.  Variable albedo surface reconstruction from stereo and shape from shading , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[5]  Leif Kobbelt,et al.  Image selection for improved Multi-View Stereo , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  James T. Kajiya,et al.  The rendering equation , 1998 .

[7]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Michael Goesele,et al.  Multi-View Stereo for Community Photo Collections , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[9]  Zhong Zhou,et al.  A new metric for measuring image-based 3D reconstruction , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[10]  P. Hanrahan,et al.  On the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian object. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[11]  Ronen Basri,et al.  Lambertian Reflectance and Linear Subspaces , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Pascal Fua,et al.  On benchmarking camera calibration and multi-view stereo for high resolution imagery , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Matthew N. Dailey,et al.  Robust Key Frame Extraction for 3D Reconstruction from Video Streams , 2010, VISAPP.

[14]  Pat Hanrahan,et al.  All-frequency shadows using non-linear wavelet lighting approximation , 2003, ACM Trans. Graph..

[15]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Jan Kautz,et al.  Precomputed radiance transfer for real-time rendering in dynamic, low-frequency lighting environments , 2002 .

[17]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[18]  Pascal Fua,et al.  Object-centered surface reconstruction: Combining multi-image stereo and shading , 1995, International Journal of Computer Vision.

[19]  Victor S. Lempitsky,et al.  Global Optimization for Shape Fitting , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.