The aim of this project is to take a set of images and combine them together into a single image. The first step is to roughly paste together the source images. The second step is to fill in any holes using "inpainting". The final step is to refine the image to make it more coherent, and also resize the image if required. The project will be based on techniques from the following papers:
A. Criminisi, P. Perez, K. Toyama, "Object Removal by Exemplar-Based Inpainting", Conference on Computer Vision and Pattern Recognition, 2003.
D. Simakov, Y. Caspi, E. Shechtman and M. Irani, "Summarizing Visual Data Using Bidirectional Similarity", Conference on Computer Vision and Pattern Recognition, 2008.