Integrating View Conditions for Image Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Jinbin, Dong, Zhen, Feng, Aosong, Zhang, Xiao, Ye, Tian, Zhou, Kaicheng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911870308319232
author Bai, Jinbin
Dong, Zhen
Feng, Aosong
Zhang, Xiao
Ye, Tian
Zhou, Kaicheng
author_facet Bai, Jinbin
Dong, Zhen
Feng, Aosong
Zhang, Xiao
Ye, Tian
Zhou, Kaicheng
contents In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of image editing tasks, especially for interior design scenes. By surveying existing object editing methodologies, we distill three essential criteria -- consistency, controllability, and harmony -- that should be met for an image editing method. In contrast to previous approaches, our framework takes the lead in satisfying all three requirements for addressing the challenge of image synthesis. Through comprehensive experiments, encompassing both quantitative assessments and qualitative comparisons with contemporary state-of-the-art methods, we present compelling evidence of our framework's superior performance across multiple dimensions. This work establishes a promising avenue for advancing image synthesis techniques and empowering precise object modifications while preserving the visual coherence of the entire composition.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16002
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Integrating View Conditions for Image Synthesis
Bai, Jinbin
Dong, Zhen
Feng, Aosong
Zhang, Xiao
Ye, Tian
Zhou, Kaicheng
Computer Vision and Pattern Recognition
In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of image editing tasks, especially for interior design scenes. By surveying existing object editing methodologies, we distill three essential criteria -- consistency, controllability, and harmony -- that should be met for an image editing method. In contrast to previous approaches, our framework takes the lead in satisfying all three requirements for addressing the challenge of image synthesis. Through comprehensive experiments, encompassing both quantitative assessments and qualitative comparisons with contemporary state-of-the-art methods, we present compelling evidence of our framework's superior performance across multiple dimensions. This work establishes a promising avenue for advancing image synthesis techniques and empowering precise object modifications while preserving the visual coherence of the entire composition.
title Integrating View Conditions for Image Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.16002