Foreground-aware Semantic Representations for Image Harmonization
About
Image harmonization is an important step in photo editing to achieve visual consistency in composite images by adjusting the appearances of foreground to make it compatible with background. Previous approaches to harmonize composites are based on training of encoder-decoder networks from scratch, which makes it challenging for a neural network to learn a high-level representation of objects. We propose a novel architecture to utilize the space of high-level features learned by a pre-trained classification network. We create our models as a combination of existing encoder-decoder architectures and a pre-trained foreground-aware deep high-resolution network. We extensively evaluate the proposed method on existing image harmonization benchmark and set up a new state-of-the-art in terms of MSE and PSNR metrics. The code and trained models are available at \url{https://github.com/saic-vul/image_harmonization}.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Harmonization | iHarmony4 HFlickr | MSE69.43 | 58 | |
| Image Harmonization | iHarmony4 (all) | MSE24.44 | 53 | |
| Image Harmonization | iHarmony4 Hday2night | MSE40.39 | 51 | |
| Image Harmonization | iHarmony4 HAdobe5k | MSE21.6 | 43 | |
| Image Harmonization | iHarmony4 HCOCO | MSE16.15 | 38 | |
| Image Harmonization | HAdobe5k iHarmony4 (test) | MSE21.9 | 37 | |
| Image Harmonization | iHarmony4 | MSE24.13 | 27 | |
| Image Harmonization | iHarmony4 HCOCO 1.0 (test) | PSNR39.2 | 11 | |
| Image Harmonization | iHarmony4 HFlickr 1.0 (test) | PSNR33.6 | 11 | |
| Image Harmonization | iHarmony4 HD2N 1.0 (test) | PSNR37.7 | 11 |