Saved in:
Bibliographic Details
Main Authors: Tao, Xinhao, Qiu, Tianyuan, Cao, Junyan, Niu, Li
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910537138307072
author Tao, Xinhao
Qiu, Tianyuan
Cao, Junyan
Niu, Li
author_facet Tao, Xinhao
Qiu, Tianyuan
Cao, Junyan
Niu, Li
contents Image harmonization aims to adjust the foreground illumination in a composite image to make it harmonious. The existing harmonization methods can only produce one deterministic result for a composite image, ignoring that a composite image could have multiple plausible harmonization results due to multiple plausible reflectances. In this work, we first propose a reflectance-guided harmonization network, which can achieve better performance with the guidance of ground-truth foreground reflectance. Then, we also design a diverse reflectance generation network to predict multiple plausible foreground reflectances, leading to multiple plausible harmonization results. The extensive experiments on the benchmark datasets demonstrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diverse Image Harmonization
Tao, Xinhao
Qiu, Tianyuan
Cao, Junyan
Niu, Li
Computer Vision and Pattern Recognition
Image harmonization aims to adjust the foreground illumination in a composite image to make it harmonious. The existing harmonization methods can only produce one deterministic result for a composite image, ignoring that a composite image could have multiple plausible harmonization results due to multiple plausible reflectances. In this work, we first propose a reflectance-guided harmonization network, which can achieve better performance with the guidance of ground-truth foreground reflectance. Then, we also design a diverse reflectance generation network to predict multiple plausible foreground reflectances, leading to multiple plausible harmonization results. The extensive experiments on the benchmark datasets demonstrate the effectiveness of our method.
title Diverse Image Harmonization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.15481