Papers › Intrinsic Image Harmonization

Intrinsic Image Harmonization

19 Jun 2021CVPR 2021 1archive 2025-07-28

Zonghui Guo, Haiyong Zheng, Yufeng Jiang, Zhaorui Gu, Bing Zheng

Compositing an image usually inevitably suffers from inharmony problem that is mainly caused by incompatibility of foreground and background from two different images with distinct surfaces and lights, corresponding to material-dependent and light-dependent characteristics, namely, reflectance and illumination intrinsic images, respectively. Therefore, we seek to solve image harmonization via separable harmonization of reflectance and illumination, i.e., intrinsic image harmonization. Our method is based on an autoencoder that disentangles composite image into reflectance and illumination for further separate harmonization. Specifically, we harmonize reflectance through material-consistency penalty, while harmonize illumination by learning and transferring light from background to foreground, moreover, we model patch relations between foreground and background of composite images in an inharmony-free learning way, to adaptively guide our intrinsic image harmonization. Both extensive experiments and ablation studies demonstrate the power of our method as well as the efficacy of each component. We also contribute a new challenging dataset for benchmarking illumination harmonization. Code and dataset are at https://github.com/zhenglab/IntrinsicHarmony.

PaperPDFCode

Code

zhenglab/IntrinsicHarmony officialmentioned in paperpytorchMIT 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

BenchmarkingImage Harmonization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Harmonization HAdobe5k(1024$\times$1024) Intrinsic MSE 56.34 #7 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) Intrinsic PSNR 34.69 #7 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) Intrinsic SSIM 0.9471 #7 of 7 Archive leaderboard report
Image Harmonization HAdobe5k(1024$\times$1024) Intrinsic fMSE 417.33 #7 of 7 Archive leaderboard report
Image Harmonization iHarmony4 Intrinsic MSE 38.71 #14 of 16 Archive leaderboard report
Image Harmonization iHarmony4 Intrinsic PSNR 35.90 #14 of 16 Archive leaderboard report
Image Harmonization iHarmony4 Intrinsic fMSE 400.29 #14 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