Seamlessly Natural: Image Stitching with Natural Appearance Preservation

TL;DR

This paper presents SENA, a geometry-driven image stitching method that preserves natural appearance and structural fidelity in challenging scenes with parallax and depth variation, outperforming traditional homography-based approaches.

Contribution

SENA introduces a hierarchical affine warping, a geometry-driven zone detection, and anchor-based seamline segmentation to improve naturalness and accuracy in image stitching.

Findings

Achieves alignment accuracy comparable to leading methods.

Significantly improves shape preservation and texture integrity.

Reduces artifacts like ghosting and smearing.

Abstract

This paper introduces SENA (SEamlessly NAtural), a geometry-driven image stitching approach that prioritizes structural fidelity in challenging real-world scenes characterized by parallax and depth variation. Conventional image stitching relies on homographic alignment, but this rigid planar assumption often fails in dual-camera setups with significant scene depth, leading to distortions such as visible warps and spherical bulging. SENA addresses these fundamental limitations through three key contributions. First, we propose a hierarchical affine-based warping strategy, combining global affine initialization with local affine refinement and smooth free-form deformation. This design preserves local shape, parallelism, and aspect ratios, thereby avoiding the hallucinated structural distortions commonly introduced by homography-based models. Second, we introduce a geometry-driven adequate zone detection mechanism that identifies parallax-minimized regions directly from the disparity consistency of RANSAC-filtered feature correspondences, without relying on semantic segmentation. Third, building upon this adequate zone, we perform anchor-based seamline cutting and segmentation, enforcing a one-to-one geometric correspondence across image pairs by construction, which effectively eliminates ghosting, duplication, and smearing artifacts in the final panorama. Extensive experiments conducted on challenging datasets demonstrate that SENA achieves alignment accuracy comparable to leading homography-based methods, while significantly outperforming them in critical visual metrics such as shape preservation, texture integrity, and overall visual realism.