Saved in:
Bibliographic Details
Main Authors: Xie, Ziqi, Lai, Xiao, Zhao, Weidong, Jiang, Siqi, Liu, Xianhui, Hou, Wenlong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.10309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915185793433600
author Xie, Ziqi
Lai, Xiao
Zhao, Weidong
Jiang, Siqi
Liu, Xianhui
Hou, Wenlong
author_facet Xie, Ziqi
Lai, Xiao
Zhao, Weidong
Jiang, Siqi
Liu, Xianhui
Hou, Wenlong
contents Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driven Inpainting Stitcher (RDIStitcher), which reformulates the image fusion and rectangling as a reference-based inpainting model, incorporating a larger modification fusion area and stronger modification intensity than previous methods. Furthermore, we introduce a self-supervised model training method, which enables the implementation of RDIStitcher without requiring labeled data by fine-tuning a Text-to-Image (T2I) diffusion model. Recognizing difficulties in assessing the quality of stitched images, we present the Multimodal Large Language Models (MLLMs)-based metrics, offering a new perspective on evaluating stitched image quality. Compared to the state-of-the-art (SOTA) method, extensive experiments demonstrate that our method significantly enhances content coherence and seamless transitions in the stitched images. Especially in the zero-shot experiments, our method exhibits strong generalization capabilities. Code: https://github.com/yayoyo66/RDIStitcher
format Preprint
id arxiv_https___arxiv_org_abs_2411_10309
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting
Xie, Ziqi
Lai, Xiao
Zhao, Weidong
Jiang, Siqi
Liu, Xianhui
Hou, Wenlong
Computer Vision and Pattern Recognition
Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driven Inpainting Stitcher (RDIStitcher), which reformulates the image fusion and rectangling as a reference-based inpainting model, incorporating a larger modification fusion area and stronger modification intensity than previous methods. Furthermore, we introduce a self-supervised model training method, which enables the implementation of RDIStitcher without requiring labeled data by fine-tuning a Text-to-Image (T2I) diffusion model. Recognizing difficulties in assessing the quality of stitched images, we present the Multimodal Large Language Models (MLLMs)-based metrics, offering a new perspective on evaluating stitched image quality. Compared to the state-of-the-art (SOTA) method, extensive experiments demonstrate that our method significantly enhances content coherence and seamless transitions in the stitched images. Especially in the zero-shot experiments, our method exhibits strong generalization capabilities. Code: https://github.com/yayoyo66/RDIStitcher
title Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.10309