Seamlessly Natural: Image Stitching with Natural Appearance Preservation

2026-01-03

AI Summary

This work addresses the limitations of traditional image stitching in dual-camera scenarios, where reliance on homography transformations often leads to artifacts such as distortion, ghosting, and spherical bulging in the presence of parallax and depth variations. To overcome these issues, the authors propose SENA, a novel method that achieves local geometric alignment through a hierarchical fusion of affine and free-form deformations. SENA introduces a geometry-consistent region detection mechanism that operates without semantic segmentation and employs anchor-guided seam cutting to enforce one-to-one geometric correspondence. Experimental results demonstrate that SENA achieves alignment accuracy comparable to state-of-the-art methods on challenging datasets while significantly outperforming them in structural fidelity, texture integrity, and visual realism.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• image stitching
• parallax
• depth variation
• structural distortion
• natural appearance

Innovation

• image stitching
• geometry-driven
• affine warping
• parallax handling
• seamline optimization