Seamless image stitching by minimizing false edges

Various applications such as mosaicing and object insertion require stitching of image parts. The stitching quality is measured visually by the similarity of the stitched image to each of the input images, and by the visibility of the seam between the stitched images. In order to define and get the best possible stitching, we introduce several formal cost functions for the evaluation of the stitching quality. In these cost functions the similarity to the input images and the visibility of the seam are defined in the gradient domain, minimizing the disturbing edges along the seam. A good image stitching will optimize these cost functions, overcoming both photometric inconsistencies and geometric misalignments between the stitched images. We study the cost functions and compare their performance for different scenarios both theoretically and practically. Our approach is demonstrated in various applications including generation of panoramic images, object blending and removal of compression artifacts. Comparisons with existing methods show the benefits of optimizing the measures in the gradient domain.

[1]  David L. Milgram,et al.  Computer Methods for Creating Photomosaics , 1975, IEEE Transactions on Computers.

[2]  Shmuel Peleg,et al.  Elimination of seams from photomosaics , 1981, Computer Graphics and Image Processing.

[3]  William H. Press,et al.  Numerical Recipes: The Art of Scientific Computing , 1987 .

[4]  Rama Chellappa,et al.  A Method for Enforcing Integrability in Shape from Shading Algorithms , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  J. E. Glynn,et al.  Numerical Recipes: The Art of Scientific Computing , 1989 .

[6]  Robert J. Vanderbei,et al.  Linear Programming: Foundations and Extensions , 1998, Kluwer international series in operations research and management service.

[7]  James Davis,et al.  Mosaics of scenes with moving objects , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[8]  Eero P. Simoncelli.  Bayesian Denoising of Visual Images in the Wavelet Domain , 1999 .

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

[10]  Martin J. Wainwright,et al.  Random cascades of Gaussian scale mixtures and their use in modeling natural images with application to denoising , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[11]  Richard Szeliski,et al.  Eliminating ghosting and exposure artifacts in image mosaics , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Guillermo Sapiro,et al.  Filling-in by joint interpolation of vector fields and gray levels , 2001, IEEE Trans. Image Process..

[13]  Yair Weiss,et al.  Deriving intrinsic images from image sequences , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[14]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[15]  Mark S. Drew,et al.  Removing Shadows from Images , 2002, ECCV.

[16]  Assaf Zomet,et al.  Learning to Perceive Transparency from the Statistics of Natural Scenes , 2002, NIPS.

[17]  Dani Lischinski,et al.  Gradient Domain High Dynamic Range Compression , 2023 .

[18]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[19]  David Salesin,et al.  Interactive digital photomontage , 2004, ACM Trans. Graph..

[20]  William T. Freeman,et al.  Learning Low-Level Vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[21]  Shmuel Peleg,et al.  Seamless Image Stitching in the Gradient Domain , 2004, ECCV.

[22]  Edward H. Adelson,et al.  Recovering intrinsic images from a single image , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.