Saved in:
Bibliographic Details
Main Authors: Xie, Ziqi, Zhao, Weidong, Liu, Xianhui, Zhao, Jian, Jia, Ning
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.14951
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914812448997376
author Xie, Ziqi
Zhao, Weidong
Liu, Xianhui
Zhao, Jian
Jia, Ning
author_facet Xie, Ziqi
Zhao, Weidong
Liu, Xianhui
Zhao, Jian
Jia, Ning
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2404_14951
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
Xie, Ziqi
Zhao, Weidong
Liu, Xianhui
Zhao, Jian
Jia, Ning
Computer Vision and Pattern Recognition
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
title Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.14951