Papers › PHNet: Patch-based Normalization for Portrait Harmonization
PHNet: Patch-based Normalization for Portrait Harmonization
Karen Efremyan, Elizaveta Petrova, Evgeny Kaskov, Alexander Kapitanov
A common problem for composite images is the incompatibility of their foreground and background components. Image harmonization aims to solve this problem, making the whole image look more authentic and coherent. Most existing solutions predict lookup tables (LUTs) or reconstruct images, utilizing various attributes of composite images. Recent approaches have primarily focused on employing global transformations like normalization and color curve rendering to achieve visual consistency, and they often overlook the importance of local visual coherence. We present a patch-based harmonization network consisting of novel Patch-based normalization (PN) blocks and a feature extractor based on statistical color transfer. Extensive experiments demonstrate the network's high generalization capability for different domains. Our network achieves state-of-the-art results on the iHarmony4 dataset. Also, we created a new human portrait harmonization dataset based on FFHQ and checked the proposed method to show the generalization ability by achieving the best metrics on it. The benchmark experiments confirm that the suggested patch-based normalization block and feature extractor effectively improve the network's capability to harmonize portraits. Our code and model baselines are publicly available.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Harmonization | FFHQH | PHNet | MSE | 16.27 | #1 of 1 | Archive leaderboard | report |
| Image Harmonization | FFHQH | PHNet | PSNR | 36.44 | #1 of 1 | Archive leaderboard | report |
| Image Harmonization | iHarmony4 | PHNet | MSE | 16.05 | #1 of 16 | Archive leaderboard | report |
| Image Harmonization | iHarmony4 | PHNet | PSNR | 38.54 | #1 of 16 | Archive leaderboard | report |
| Image Harmonization | iHarmony4 | PHNet | fMSE | 178.11 | #1 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