Papers › High-Resolution Image Harmonization via Collaborative Dual Transformations
High-Resolution Image Harmonization via Collaborative Dual Transformations
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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