Superresolution texture maps for multiview reconstruction

We study the scenario of a multiview setting, where several calibrated views of a textured object with known surface geometry are available. The objective is to estimate a diffuse texture map as precisely as possible. A superresolution image formation model based on the camera properties leads to a total variation energy for the desired texture map, which can be recovered as the minimizer of the functional by solving the Euler-Lagrange equation on the surface. The PDE is transformed to planar texture space via an automatically created conformal atlas, where it can be solved using total variation deblurring. The proposed approach allows to recover a high-resolution, high-quality texture map even from lower-resolution photographs, which is of interest for a variety of image-based modeling applications.

[1]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[2]  Anita Sellent,et al.  Floating Textures , 2008, Comput. Graph. Forum.

[3]  Reinhard Koch,et al.  Multi Viewpoint Stereo from Uncalibrated Video Sequences , 1998, ECCV.

[4]  Jean-Philippe Pons,et al.  Seamless image-based texture atlases using multi-band blending , 2008, 2008 19th International Conference on Pattern Recognition.

[5]  Holly E. Rushmeier,et al.  High-Quality Texture Reconstruction from Multiple Scans , 2001, IEEE Trans. Vis. Comput. Graph..

[6]  S. Osher,et al.  Variational problems and PDEs on implicit surfaces , 2001, Proceedings IEEE Workshop on Variational and Level Set Methods in Computer Vision.

[7]  Takeo Kanade,et al.  Limits on Super-Resolution and How to Break Them , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Kai Hormann,et al.  Surface Parameterization: a Tutorial and Survey , 2005, Advances in Multiresolution for Geometric Modelling.

[9]  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).

[10]  Hanno Scharr,et al.  A Scheme for Coherence-Enhancing Diffusion Filtering with Optimized Rotation Invariance , 2002, J. Vis. Commun. Image Represent..

[11]  Hans-Peter Seidel,et al.  A Silhouette-Based Algorithm for Texture Registration and Stitching , 2001, Graph. Model..

[12]  Paul M. Thompson,et al.  Surface parameterization using Riemann surface structure , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Bruno Lévy,et al.  Least squares conformal maps for automatic texture atlas generation , 2002, ACM Trans. Graph..

[14]  Daniel Cremers,et al.  Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains , 2008, ECCV.

[15]  Tony F. Chan,et al.  Color TV: total variation methods for restoration of vector-valued images , 1998, IEEE Trans. Image Process..

[16]  Peter Cheeseman,et al.  Super-Resolved Surface Reconstruction from Multiple Images , 1996 .

[17]  Hans-Peter Seidel,et al.  Seeing People in Different Light — Joint Shape , Motion , and Reflectance Capture , 2007 .

[18]  Jos Stam,et al.  Flows on surfaces of arbitrary topology , 2003, ACM Trans. Graph..

[19]  Jan Flusser,et al.  A Unified Approach to Superresolution and Multichannel Blind Deconvolution , 2007, IEEE Transactions on Image Processing.

[20]  Thomas Brox,et al.  PDE-Based Deconvolution with Forward-Backward Diffusivities and Diffusion Tensors , 2005, Scale-Space.

[21]  Hideo Saito,et al.  Generation of 3D model with super resolved texture from image sequence , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[22]  Daniel Cremers,et al.  A Superresolution Framework for High-Accuracy Multiview Reconstruction , 2009, DAGM-Symposium.

[23]  S. Yau,et al.  Global conformal surface parameterization , 2003 .

[24]  Lok Ming Lui,et al.  Solving PDEs on Manifolds with Global Conformal Parametriazation , 2005, VLSM.

[25]  Andrew Zisserman,et al.  Super-resolution from multiple views using learnt image models , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[26]  Daniel Cremers,et al.  High resolution motion layer decomposition using dual-space graph cuts , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Manuele Bicego,et al.  Unsupervised scene analysis: a hidden Markov model approach , 2006 .

[28]  Luc Van Gool,et al.  Optical flow based super-resolution: A probabilistic approach , 2007, Comput. Vis. Image Underst..

[29]  Victor S. Lempitsky,et al.  Seamless Mosaicing of Image-Based Texture Maps , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.