Deep Image Harmonization in Dual Color Spaces

5 Aug 2023  ·  Linfeng Tan, Jiangtong Li, Li Niu, Liqing Zhang ·

Image harmonization is an essential step in image composition that adjusts the appearance of composite foreground to address the inconsistency between foreground and background. Existing methods primarily operate in correlated $RGB$ color space, leading to entangled features and limited representation ability. In contrast, decorrelated color space (e.g., $Lab$) has decorrelated channels that provide disentangled color and illumination statistics. In this paper, we explore image harmonization in dual color spaces, which supplements entangled $RGB$ features with disentangled $L$, $a$, $b$ features to alleviate the workload in harmonization process. The network comprises a $RGB$ harmonization backbone, an $Lab$ encoding module, and an $Lab$ control module. The backbone is a U-Net network translating composite image to harmonized image. Three encoders in $Lab$ encoding module extract three control codes independently from $L$, $a$, $b$ channels, which are used to manipulate the decoder features in harmonization backbone via $Lab$ control module. Our code and model are available at \href{https://github.com/bcmi/DucoNet-Image-Harmonization}{https://github.com/bcmi/DucoNet-Image-Harmonization}.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Harmonization HAdobe5k(1024$\times$1024) DucoNet PSNR 41.37 # 2
MSE 10.94 # 1
fMSE 80.69 # 7
SSIM 0.9886 # 2
Image Harmonization iHarmony4 DucoNet MSE 18.47 # 3
PSNR 39.17 # 4
fMSE 212.53 # 12

Methods