Single-Perspective Warps in Natural Image Stitching

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.

arXiv comment10 pages, 10 figures

Cited by in corpus (5)

• Deep Rectangling for Image Stitching: A Learning Baseline
• Image Stitching Based on Planar Region Consensus
• TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models
• Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation
• Unified Vertex Motion Estimation for Integrated Video Stabilization and Stitching in Tractor-Trailer Wheeled Robots