SemanticStitch: Enhancing Image Coherence through Foreground-Aware Seam Carving

TL;DR

SemanticStitch is a deep learning framework that improves image stitching by incorporating semantic information to preserve foreground object integrity and enhance visual coherence.

Contribution

It introduces a novel semantic-aware loss function and datasets, significantly advancing the quality of stitched images compared to traditional methods.

Findings

Substantial improvement in stitching quality over traditional methods.

Effective preservation of foreground object integrity.

Robust performance demonstrated on two real-world datasets.

Abstract

Image stitching often faces challenges due to varying capture angles, positional differences, and object movements, leading to misalignments and visual discrepancies. Traditional seam carving methods neglect semantic information, causing disruptions in foreground continuity. We introduce SemanticStitch, a deep learning-based framework that incorporates semantic priors of foreground objects to preserve their integrity and enhance visual coherence. Our approach includes a novel loss function that emphasizes the semantic integrity of salient objects, significantly improving stitching quality. We also present two specialized real-world datasets to evaluate our method's effectiveness. Experimental results demonstrate substantial improvements over traditional techniques, providing robust support for practical applications.