Texture super-resolution for 3D reconstruction

We describe a method for producing a high quality texture atlas for 3D models by fully exploiting the information contained in dense video sequences via super-resolution techniques. The intrinsic precision limitations of multi-view reconstruction techniques are analyzed and overcome. Compared to similar methods that rely on camera pose correction and geometry refinement, our subpixel image registration technique directly corrects the registration error in the image domain is much more efficient. We illustrate our method by enhancing the texture resolution of a 3D model produced by a state of the art reconstruction software.

[1]  Michael Elad,et al.  A fast super-resolution reconstruction algorithm for pure translational motion and common space-invariant blur , 2001, IEEE Trans. Image Process..

[2]  Russell C Hardie,et al.  Fast super-resolution using an adaptive Wiener filter with robustness to local motion. , 2012, Optics express.

[3]  Michael Elad,et al.  Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images , 1997, IEEE Trans. Image Process..

[4]  Andrew I. Comport,et al.  Super-resolution 3D tracking and mapping , 2013, 2013 IEEE International Conference on Robotics and Automation.

[5]  Michael Goesele,et al.  Let There Be Color! Large-Scale Texturing of 3D Reconstructions , 2014, ECCV.

[6]  Jörg Stückler,et al.  Super-resolution Keyframe Fusion for 3D Modeling with High-Quality Textures , 2015, 2015 International Conference on 3D Vision.

[7]  Horst Bischof,et al.  Building with drones: Accurate 3D facade reconstruction using MAVs , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Daniel Cohen-Or,et al.  Seamless Montage for Texturing Models , 2010, Comput. Graph. Forum.

[9]  Stéphane Landeau.  Evaluation of super-resolution imager with binary fractal test target , 2014, Security and Defence.

[10]  Daniel Cremers,et al.  A Super-Resolution Framework for High-Accuracy Multiview Reconstruction , 2013, International Journal of Computer Vision.

[11]  J.-Y. Bouguet,et al.  Pyramidal implementation of the lucas kanade feature tracker , 1999 .

[12]  Aurélien Plyer,et al.  Massively parallel Lucas Kanade optical flow for real-time video processing applications , 2014, Journal of Real-Time Image Processing.