Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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}.

Konstantin Sofiiuk, Polina Popenova, Anton Konushin• 2020

Related benchmarks

TaskDatasetResultRank
Image HarmonizationiHarmony4 HFlickr
MSE69.43
58
Image HarmonizationiHarmony4 (all)
MSE24.44
53
Image HarmonizationiHarmony4 Hday2night
MSE40.39
51
Image HarmonizationiHarmony4 HAdobe5k
MSE21.6
43
Image HarmonizationiHarmony4 HCOCO
MSE16.15
38
Image HarmonizationHAdobe5k iHarmony4 (test)
MSE21.9
37
Image HarmonizationiHarmony4
MSE24.13
27
Image HarmonizationiHarmony4 HCOCO 1.0 (test)
PSNR39.2
11
Image HarmonizationiHarmony4 HFlickr 1.0 (test)
PSNR33.6
11
Image HarmonizationiHarmony4 HD2N 1.0 (test)
PSNR37.7
11
Showing 10 of 22 rows

Other info

Follow for update