Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model

TL;DR

This paper introduces SRStitcher, a unified inpainting-based approach to image stitching that simplifies the pipeline, eliminates the need for multiple models, and improves performance and stability through a single inference process.

Contribution

It reformulates fusion and rectangling as an inpainting task, integrating them into a single, training-free model using a pre-trained diffusion network.

Findings

Outperforms state-of-the-art methods in accuracy.

Demonstrates high generalization across diverse datasets.

Offers enhanced stability and interpretability.

Abstract

Deep learning-based image stitching pipelines are typically divided into three cascading stages: registration, fusion, and rectangling. Each stage requires its own network training and is tightly coupled to the others, leading to error propagation and posing significant challenges to parameter tuning and system stability. This paper proposes the Simple and Robust Stitcher (SRStitcher), which revolutionizes the image stitching pipeline by simplifying the fusion and rectangling stages into a unified inpainting model, requiring no model training or fine-tuning. We reformulate the problem definitions of the fusion and rectangling stages and demonstrate that they can be effectively integrated into an inpainting task. Furthermore, we design the weighted masks to guide the reverse process in a pre-trained largescale diffusion model, implementing this integrated inpainting task in a single inference. Through extensive experimentation, we verify the interpretability and generalization capabilities of this unified model, demonstrating that SRStitcher outperforms state-of-the-art methods in both performance and stability. Code: https://github.com/yayoyo66/SRStitcher