Papers › High-Resolution Image Harmonization via Collaborative Dual Transformations

High-Resolution Image Harmonization via Collaborative Dual Transformations

14 Sep 2021CVPR 2022 1arXiv:2109.06671archive 2025-07-28

Wenyan Cong, Xinhao Tao, Li Niu, Jing Liang, Xuesong Gao, Qihao Sun, Liqing Zhang

Given a composite image, image harmonization aims to adjust the foreground to make it compatible with the background. High-resolution image harmonization is in high demand, but still remains unexplored. Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context. Recent deep learning methods learn the dense pixel-to-pixel transformation which could generate harmonious outputs, but are highly constrained in low resolution. In this work, we propose a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel-to-pixel transformation and RGB-to-RGB transformation coherently in an end-to-end network. Our CDTNet consists of a low-resolution generator for pixel-to-pixel transformation, a color mapping module for RGB-to-RGB transformation, and a refinement module to take advantage of both. Extensive experiments on high-resolution benchmark dataset and our created high-resolution real composite images demonstrate that our CDTNet strikes a good balance between efficiency and effectiveness. Our used datasets can be found in https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization.

PaperPDFConference PDFCode

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

Code

bcmi/CDTNet-High-Resolution-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

Image HarmonizationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Harmonization HAdobe5k(1024$\times$1024) CDTNet MSE 21.24 #3 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) CDTNet PSNR 38.77 #3 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) CDTNet SSIM 0.9868 #3 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) CDTNet fMSE 152.13 #3 of 7 Archive leaderboard report
Image Harmonization iHarmony4 CDTNet MSE 23.75 #6 of 16 Archive leaderboard report
Image Harmonization iHarmony4 CDTNet PSNR 38.23 #6 of 16 Archive leaderboard report
Image Harmonization iHarmony4 CDTNet fMSE - #6 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.

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