Image Harmonization
42 papers with code • 3 benchmarks • 2 datasets
Image harmonization aims to modify the color of the composited region with respect to the specific background.
iHarmony4
Most implemented papers
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.
Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization
mengweiren/segmentation-renormalized-harmonization
•
•
Deep networks are now ubiquitous in large-scale multi-center imaging studies.
Deep Image Harmonization by Bridging the Reality Gap
bcmi/Rendered_Image_Harmonization_Datasets
•
•
Image harmonization has been significantly advanced with large-scale harmonization dataset.
Inharmonious Region Localization
bcmi/DIRL
•
•
The advance of image editing techniques allows users to create artistic works, but the manipulated regions may be incompatible with the background.
Region-aware Adaptive Instance Normalization for Image Harmonization
To ensure the visual style consistency between the foreground and the background, in this paper, we treat image harmonization as a style transfer problem.
Intrinsic Image Harmonization
zhenglab/IntrinsicHarmony
•
•
CVPR 2021
Specifically, we harmonize reflectance through material-consistency penalty, while harmonize illumination by learning and transferring light from background to foreground, moreover, we model patch relations between foreground and background of composite images in an inharmony-free learning way, to adaptively guide our intrinsic image harmonization.
SSH: A Self-Supervised Framework for Image Harmonization
vita-group/ssharmonization
•
•
ICCV 2021
Image harmonization aims to improve the quality of image compositing by matching the "appearance" (\eg, color tone, brightness and contrast) between foreground and background images.
High-Resolution Image Harmonization via Collaborative Dual Transformations
bcmi/CDTNet-High-Resolution-Image-Harmonization
•
•
CVPR 2022
Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context.
Deep residual inception encoder-decoder network for amyloid PET harmonization
jaygshah/RIED-Net
•
•
Alzheimer's and Dementia 2022
Multiple positron emission tomography (PET) tracers are available for amyloid imaging, posing a significant challenge to consensus interpretation and quantitative analysis.
SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity.
