Correspondence Insertion for As-Projective-As-Possible Image Stitching

TL;DR

This paper introduces a correspondence insertion method for APAP image warps, automatically improving alignment in panoramic stitching by adding correspondences in misaligned regions, enhancing flexibility without increasing distortion.

Contribution

It presents a novel automatic correspondence insertion technique that enhances APAP warps for better panoramic image stitching in challenging scenes.

Findings

Improved alignment in panoramic stitching with misaligned regions.

Enhanced warp flexibility without increased distortion.

Effective in scenes with significant depth parallax.

Abstract

Spatially varying warps are increasingly popular for image alignment. In particular, as-projective-as-possible (APAP) warps have been proven effective for accurate panoramic stitching, especially in cases with significant depth parallax that defeat standard homographic warps. However, estimating spatially varying warps requires a sufficient number of feature matches. In image regions where feature detection or matching fail, the warp loses guidance and is unable to accurately model the true underlying warp, thus resulting in poor registration. In this paper, we propose a correspondence insertion method for APAP warps, with a focus on panoramic stitching. Our method automatically identifies misaligned regions, and inserts appropriate point correspondences to increase the flexibility of the warp and improve alignment. Unlike other warp varieties, the underlying projective regularization of APAP warps reduces overfitting and geometric distortion, despite increases to the warp complexity. Comparisons with recent techniques for parallax-tolerant image stitching demonstrate the effectiveness and simplicity of our approach.