Depth-Supervised Fusion Network for Seamless-Free Image Stitching

TL;DR

This paper introduces a depth-aware image stitching method that reduces parallax effects, improves alignment accuracy, and produces seamless results through a multi-stage mechanism, graph-based seam optimization, and efficiency enhancements.

Contribution

It presents a novel depth-consistency-constrained stitching approach with a multi-stage alignment, optimal seam detection, and a reparameterization strategy for improved efficiency.

Findings

Outperforms existing stitching methods in quality and accuracy

Effectively mitigates ghosting and misalignment caused by parallax

Achieves seamless stitching with improved computational efficiency

Abstract

Image stitching synthesizes images captured from multiple perspectives into a single image with a broader field of view. The significant variations in object depth often lead to large parallax, resulting in ghosting and misalignment in the stitched results. To address this, we propose a depth-consistency-constrained seamless-free image stitching method. First, to tackle the multi-view alignment difficulties caused by parallax, a multi-stage mechanism combined with global depth regularization constraints is developed to enhance the alignment accuracy of the same apparent target across different depth ranges. Second, during the multi-view image fusion process, an optimal stitching seam is determined through graph-based low-cost computation, and a soft-seam region is diffused to precisely locate transition areas, thereby effectively mitigating alignment errors induced by parallax and achieving natural and seamless stitching results. Furthermore, considering the computational overhead in the shift regression process, a reparameterization strategy is incorporated to optimize the structural design, significantly improving algorithm efficiency while maintaining optimal performance. Extensive experiments demonstrate the superior performance of the proposed method against the existing methods. Code is available at https://github.com/DLUT-YRH/DSFN.