Papers › Deep Image Harmonization in Dual Color Spaces

Deep Image Harmonization in Dual Color Spaces

5 Aug 2023arXiv:2308.02813archive 2025-07-28

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}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bcmi/duconet-image-harmonization officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderImage Harmonization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Harmonization HAdobe5k(1024$\times$1024) DucoNet MSE 10.94 #1 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) DucoNet PSNR 41.37 #1 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) DucoNet SSIM 0.9886 #1 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) DucoNet fMSE 80.69 #1 of 7 Archive leaderboard report
Image Harmonization iHarmony4 DucoNet MSE 18.47 #3 of 16 Archive leaderboard report
Image Harmonization iHarmony4 DucoNet PSNR 39.17 #3 of 16 Archive leaderboard report
Image Harmonization iHarmony4 DucoNet fMSE 212.53 #3 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections