Image stitching with perspective-preserving warping

TL;DR

This paper introduces a perspective-preserving warping method for image stitching that combines local projective and similarity transformations to improve alignment and reduce distortions in challenging scenarios.

Contribution

It proposes a novel warping technique that smoothly transitions from projective to similarity transformations, enhancing stitching quality in complex scenes.

Findings

Improved alignment accuracy in challenging images

Reduced projective distortions and perspective errors

Efficient performance demonstrated on diverse datasets

Abstract

Image stitching algorithms often adopt the global transformation, such as homography, and work well for planar scenes or parallax free camera motions. However, these conditions are easily violated in practice. With casual camera motions, variable taken views, large depth change, or complex structures, it is a challenging task for stitching these images. The global transformation model often provides dreadful stitching results, such as misalignments or projective distortions, especially perspective distortion. To this end, we suggest a perspective-preserving warping for image stitching, which spatially combines local projective transformations and similarity transformation. By weighted combination scheme, our approach gradually extrapolates the local projective transformations of the overlapping regions into the non-overlapping regions, and thus the final warping can smoothly change from projective to similarity. The proposed method can provide satisfactory alignment accuracy as well as reduce the projective distortions and maintain the multi-perspective view. Experiments on a variety of challenging images confirm the efficiency of the approach.