Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Xiaoyu, Zhou, Teng, Zhang, Xinlong, Wei, Jia, Tang, Yongchuan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.18830
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913779454836736
author Zhang, Xiaoyu
Zhou, Teng
Zhang, Xinlong
Wei, Jia
Tang, Yongchuan
author_facet Zhang, Xiaoyu
Zhou, Teng
Zhang, Xinlong
Wei, Jia
Tang, Yongchuan
contents Diffusion models have recently gained recognition for generating diverse and high-quality content, especially in image synthesis. These models excel not only in creating fixed-size images but also in producing panoramic images. However, existing methods often struggle with spatial layout consistency when producing high-resolution panoramas due to the lack of guidance on the global image layout. This paper introduces the Multi-Scale Diffusion (MSD), an optimized framework that extends the panoramic image generation framework to multiple resolution levels. Our method leverages gradient descent techniques to incorporate structural information from low-resolution images into high-resolution outputs. Through comprehensive qualitative and quantitative evaluations against prior work, we demonstrate that our approach significantly improves the coherence of high-resolution panorama generation.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18830
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Scale Diffusion: Enhancing Spatial Layout in High-Resolution Panoramic Image Generation
Zhang, Xiaoyu
Zhou, Teng
Zhang, Xinlong
Wei, Jia
Tang, Yongchuan
Computer Vision and Pattern Recognition
Diffusion models have recently gained recognition for generating diverse and high-quality content, especially in image synthesis. These models excel not only in creating fixed-size images but also in producing panoramic images. However, existing methods often struggle with spatial layout consistency when producing high-resolution panoramas due to the lack of guidance on the global image layout. This paper introduces the Multi-Scale Diffusion (MSD), an optimized framework that extends the panoramic image generation framework to multiple resolution levels. Our method leverages gradient descent techniques to incorporate structural information from low-resolution images into high-resolution outputs. Through comprehensive qualitative and quantitative evaluations against prior work, we demonstrate that our approach significantly improves the coherence of high-resolution panorama generation.
title Multi-Scale Diffusion: Enhancing Spatial Layout in High-Resolution Panoramic Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.18830