Multiple Combined Constraints for Image Stitching

Abstract

Several approaches to image stitching use different constraints to estimate the motion model between image pairs. These constraints can be roughly divided into two categories: geometric constraints and photometric constraints. In this paper, geometric and photometric constraints are combined to improve the alignment quality, which is based on the observation that these two kinds of constraints are complementary. On the one hand, geometric constraints (e.g., point and line correspondences) are usually spatially biased and are insufficient in some extreme scenes, while photometric constraints are always evenly and densely distributed. On the other hand, photometric constraints are sensitive to displacements and are not suitable for images with large parallaxes, while geometric constraints are usually imposed by feature matching and are more robust to handle parallaxes. The proposed method therefore combines them together in an efficient mesh-based image warping framework. It achieves better alignment quality than methods only with geometric constraints, and can handle larger parallax than photometric-constraintbased method. Experimental results on various images illustrate that the proposed method outperforms representative state-of-the-art image stitching methods reported in the literature.

Vanishing Point Guided Natural Image Stitching

“…In other words, the naturalness improvement achieved by our VPG is compatible with high alignment accuracy. Figure 14 and Figure 15 present two groups of panoramas produced by different methods and report the associated GDIC values and the MSE of alignment accuracy [7], [41], [20], [6]. By combining VPG with DFW and GCPW, the output panoramas not only have more natural looks than GSP, but also have higher alignment accuracy than both GSP and the original VPG.…”

“…Methods started to flourish since 2007, when Brown and Lowe [1] proposed to use SIFT features [2] to fit a global homography model for stitching. Since then, various methods were developed to further improve the stitching performance, including the spatially varying methods [3], [4] with a higher degree of freedom for good alignment accuracy, and the combined-constraints based methods [5], [6], [7] for improving stitching robustness. The technique of mesh deformation [8] is also adopted to stitching since it has high alignment quality and is highly scalable to some specific stitching purposes, such as stereoscopic stitching [9], [10], [11].…”