Making images real again: A comprehensive survey on deep image composition

L Niu, W Cong, L Liu, Y Hong, B Zhang, J Liang… - arXiv preprint arXiv …, 2021 - arxiv.org
As a common image editing operation, image composition aims to combine the foreground
from one image and another background image, resulting in a composite image. However …

Harmonizer: Learning to perform white-box image and video harmonization

Z Ke, C Sun, L Zhu, K Xu, RWH Lau - European Conference on Computer …, 2022 - Springer
Recent works on image harmonization solve the problem as a pixel-wise image translation
task via large autoencoders. They have unsatisfactory performances and slow inference …

Pct-net: Full resolution image harmonization using pixel-wise color transformations

JJA Guerreiro, M Nakazawa… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this paper, we present PCT-Net, a simple and general image harmonization method that
can be easily applied to images at full resolution. The key idea is to learn a parameter …

Coordfill: Efficient high-resolution image inpainting via parameterized coordinate querying

W Liu, X Cun, CM Pun, M Xia, Y Zhang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Image inpainting aims to fill the missing hole of the input. It is hard to solve this task
efficiently when facing high-resolution images due to two reasons:(1) Large reception field …

Semi-supervised parametric real-world image harmonization

K Wang, M Gharbi, H Zhang, Z Xia… - Proceedings of the …, 2023 - openaccess.thecvf.com
Learning-based image harmonization techniques are usually trained to undo synthetic
global transformations, applied to a masked foreground in a single ground truth photo. This …

High-resolution document shadow removal via a large-scale real-world dataset and a frequency-aware shadow erasing net

Z Li, X Chen, CM Pun, X Cun - 2023 IEEE/CVF International …, 2023 - ieeexplore.ieee.org
Shadows often occur when we capture the document with casual equipment, which
influences the visual quality and readability of the digital copies. Different from the …

Deep image harmonization with learnable augmentation

L Niu, J Cao, W Cong, L Zhang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The goal of image harmonization is adjusting the foreground appearance in a composite
image to make the whole image harmonious. To construct paired training images, existing …

Hierarchical dynamic image harmonization

H Chen, Z Gu, Y Li, J Lan, C Meng, W Wang… - Proceedings of the 31st …, 2023 - dl.acm.org
Image harmonization is a critical task in computer vision, which aims to adjust the
foreground to make it compatible with the background. Recent works mainly focus on using …

Lemart: Label-efficient masked region transform for image harmonization

S Liu, CP Huynh, C Chen, M Arap… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present a simple yet effective self-supervised pretraining method for image
harmonization which can leverage large-scale unannotated image datasets. To achieve this …

Learning image harmonization in the linear color space

K Xu, GP Hancke, RWH Lau - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Harmonizing cut-and-paste images into perceptually realistic ones is challenging, as it
requires a full understanding of the discrepancies between the background of the target …