Stitching contaminated images

Image stitching has long been studied in computer vision and has been applied to many fields. However, when the input images contain moving objects and meanwhile are noisy or partially contaminated, it remains a challenge to get a satisfactory clean panorama. In this paper, we propose to tackle both the challenges, i.e., denoising and stitching, by proposing a new energy function in a unified way. Such an energy model is however non-submodule, making the widely used optimization algorithms, such as graph cuts, hard to be used directly. We then generalize the recently proposed Graduated Non-Convexity and Concavity Procedure (GNCCP) to approximately minimize the energy. Comparative experiments validate the efficacy of the proposed energy function on both image denoising and stitching. Besides, the results also show the validity of the generalized-GNCCP on minimizing non-submodule function.