Single-Perspective Warps in Natural Image Stitching

TL;DR

This paper introduces two novel single-perspective warps for natural image stitching that improve perspective consistency while managing distortions, outperforming existing methods in various evaluations.

Contribution

It proposes a parametric warp and a mesh-based warp specifically designed for single-perspective image stitching, enhancing perspective consistency and naturalness.

Findings

The proposed warps outperform state-of-the-art methods like homography and APAP.

The mesh-based warp effectively balances alignment, naturalness, and distortion.

Evaluation shows superior performance in perceptual quality and geometric accuracy.

Abstract

Results of image stitching can be perceptually divided into single-perspective and multiple-perspective. Compared to the multiple-perspective result, the single-perspective result excels in perspective consistency but suffers from projective distortion. In this paper, we propose two single-perspective warps for natural image stitching. The first one is a parametric warp, which is a combination of the as-projective-as-possible warp and the quasi-homography warp via dual-feature. The second one is a mesh-based warp, which is determined by optimizing a total energy function that simultaneously emphasizes different characteristics of the single-perspective warp, including alignment, naturalness, distortion and saliency. A comprehensive evaluation demonstrates that the proposed warp outperforms some state-of-the-art warps, including homography, APAP, AutoStitch, SPHP and GSP.