Deep Image Harmonization via Domain Verification

11/27/2019
by   Wenyan Cong, et al.
5

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image. Image harmonization, aiming to make the foreground compatible with the background, is a promising yet challenging task. However, the lack of high-quality publicly available dataset for image harmonization greatly hinders the development of image harmonization techniques. In this work, we contribute an image harmonization dataset by generating synthesized composite images based on COCO (resp., Adobe5k, Flickr, day2night) dataset, leading to our HCOCO (resp., HAdobe5k, HFlickr, Hday2night) sub-dataset. Moreover, we propose a new deep image harmonization method with a novel domain verification discriminator, enlightened by the following insight. Specifically, incompatible foreground and background belong to two different domains, so we need to translate the domain of foreground to the same domain as background. Our proposed domain verification discriminator can play such a role by pulling close the domains of foreground and background. Extensive experiments on our constructed dataset demonstrate the effectiveness of our proposed method. Our dataset is released in https://github.com/bcmi/Image_Harmonization_Datasets.

READ FULL TEXT

page 17

page 18

page 19

page 20

page 21

page 22

page 23

page 24

research
08/28/2019

Image Harmonization Datasets: HCOCO, HAdobe5k, HFlickr, and Hday2night

Image composition is an important operation in image processing, but the...
research
09/19/2020

BargainNet: Background-Guided Domain Translation for Image Harmonization

Image composition is a fundamental operation in image editing field. How...
research
09/01/2023

DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus Segmentation

Nucleus segmentation is usually the first step in pathological image ana...
research
12/17/2022

Painterly Image Harmonization in Dual Domains

Image harmonization aims to produce visually harmonious composite images...
research
12/02/2021

NeurSF: Neural Shading Field for Image Harmonization

Image harmonization aims at adjusting the appearance of the foreground t...
research
03/19/2021

Carton dataset synthesis based on foreground texture replacement

One major impediment in rapidly deploying object detection models for in...
research
11/04/2020

Deep Image Compositing

Image compositing is a task of combining regions from different images t...

Please sign up or login with your details

Forgot password? Click here to reset