A geodesic-preserving method for image warping

The manipulation of panoramic/wide-angle images is usually achieved via image warping. Though various techniques have been developed for preserving shapes and straight lines for warping, these are not sufficient for panoramic/wide-angle images. The image projections will turn the straight lines into curved “geodesic lines”, and it is fundamentally impossible to keep all these lines straight. In this work, we propose a geodesic-preserving method for content-aware image warping. An energy term is introduced to preserve the geodesic appearance of the geodesic lines, and can be used with shape-preserving terms. Our method is demonstrated in various applications, including rectangling panoramas, resizing panoramic/wide-angle images, and wide-angle image manipulation. An extension to ellipse preservation for general images is also presented.

[1]  Richard Szeliski,et al.  Creating full view panoramic image mosaics and environment maps , 1997, SIGGRAPH.

[2]  Shmuel Peleg,et al.  Mosaicing on Adaptive Manifolds , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  P. Perona,et al.  Squaring the circle in panoramas , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[4]  Scott Schaefer,et al.  Image deformation using moving least squares , 2006, ACM Trans. Graph..

[5]  Tong-Yee Lee,et al.  Motion-based video retargeting with optimized crop-and-warp , 2010, SIGGRAPH 2010.

[6]  Maneesh Agrawala,et al.  Optimizing content-preserving projections for wide-angle images , 2009, SIGGRAPH '09.

[7]  O. Sorkine,et al.  Motion-based video retargeting with optimized crop-and-warp , 2010, ACM Trans. Graph..

[8]  Zehdreh Allen-Lafayette,et al.  Flattening the Earth, Two Thousand Years of Map Projections , 1998 .

[9]  Jian Sun,et al.  Content-Aware Rotation , 2013, 2013 IEEE International Conference on Computer Vision.

[10]  Dani Lischinski,et al.  Locally Adapted Projections to Reduce Panorama Distortions , 2009, Comput. Graph. Forum.

[11]  Jian Sun,et al.  Rectangling panoramic images via warping , 2013, ACM Trans. Graph..

[12]  Denis Zorin,et al.  Correction of geometric perceptual distortions in pictures , 1995, SIGGRAPH.

[13]  Michael S. Brown,et al.  As-Projective-As-Possible Image Stitching with Moving DLT , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Michael F. Cohen,et al.  Capturing and viewing gigapixel images , 2007, ACM Trans. Graph..

[15]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Yung-Yu Chuang,et al.  A line-structure-preserving approach to image resizing , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Olga Sorkine-Hornung,et al.  Optimized scale-and-stretch for image resizing , 2008, SIGGRAPH Asia '08.

[18]  Jian Sun,et al.  Bundled camera paths for video stabilization , 2013, ACM Trans. Graph..

[19]  S. Avidan,et al.  Seam carving for content-aware image resizing , 2007, SIGGRAPH 2007.

[20]  Takeo Igarashi,et al.  As-rigid-as-possible shape manipulation , 2005, ACM Trans. Graph..

[21]  Maneesh Agrawala,et al.  Image warps for artistic perspective manipulation , 2010, ACM Trans. Graph..

[22]  Ralph R. Martin,et al.  A Shape‐Preserving Approach to Image Resizing , 2009, Comput. Graph. Forum.

[23]  Rafael Grompone von Gioi,et al.  LSD: A Fast Line Segment Detector with a False Detection Control , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.