Image Harmonization

25 papers with code • 2 benchmarks • 1 datasets

Image harmonization aims to modify the color of the composited region with respect to the specific background.

Libraries

Use these libraries to find Image Harmonization models and implementations

Datasets


Most implemented papers

Inharmonious Region Localization

bcmi/DIRL 19 Apr 2021

The advance of image editing techniques allows users to create artistic works, but the manipulated regions may be incompatible with the background.

Deep Image Harmonization

wasidennis/DeepHarmonization CVPR 2017

Compositing is one of the most common operations in photo editing.

BargainNet: Background-Guided Domain Translation for Image Harmonization

bcmi/BargainNet-Image-Harmonization 19 Sep 2020

Therefore, we propose an image harmonization network with a novel domain code extractor and well-tailored triplet losses, which could capture the background domain information to guide the foreground harmonization.

Improving the Harmony of the Composite Image by Spatial-Separated Attention Module

vinthony/s2am 15 Jul 2019

Thus, we address the problem of Image Harmonization: Given a spliced image and the mask of the spliced region, we try to harmonize the "style" of the pasted region with the background (non-spliced region).

Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night

bcmi/Image_Harmonization_Datasets 28 Aug 2019

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.

DoveNet: Deep Image Harmonization via Domain Verification

bcmi/Image_Harmonization_Datasets CVPR 2020

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.

Foreground-aware Semantic Representations for Image Harmonization

saic-vul/image_harmonization 1 Jun 2020

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.

Generative Hierarchical Features from Synthesizing Images

genforce/ghfeat CVPR 2021

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data.

Image Harmonization With Transformer

zhenglab/harmonytransformer ICCV 2021

Current solutions mainly adopt an encoder-decoder architecture with convolutional neural network (CNN) to capture the context of composite images, trying to understand what it looks like in the surrounding background near the foreground.