Image-Harmonization-Dataset-iHarmony4
Image Harmonization Dataset
A collection of datasets and tools for training algorithms to harmonize images by adjusting the appearance of foreground regions to match the background.
[CVPR 2020] The first large-scale public benchmark dataset for image harmonization. The code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for image harmonization, image composition, etc.
768 stars
16 watching
99 forks
Language: MATLAB
last commit: over 2 years agocomposite-imagesdeep-image-compositiondeep-image-harmonizationdomain-translationdomain-verificationimage-compositionimage-harmonizationimage-harmonization-dataset
Related projects:
| Repository | Description | Stars |
|---|---|---|
 wasidennis/deepharmonization | Reimplements a deep learning model to harmonize images from different illumination conditions | 150 |
| bcmi/controlcom-image-composition | An image composition model that allows for controllable blending of images by adjusting foreground attributes such as pose and illumination. | 151 |
| bcmi/libcom | An image composition toolbox that integrates various methods to generate realistic composite images from different sources. | 558 |
 zhengpeng7/birefnet | An open-source implementation of an image segmentation model that combines background removal and object detection capabilities. | 1,484 |
| bcmi/dreamcom-image-composition | A framework for customizing generative models to insert subjects into background images based on reference images | 19 |
| bcmi/foreground-object-search-dataset-fosd | A collection of datasets and tools for foreground object search research | 20 |
 vinthony/s2am | Improving image composition by harmonizing the style of a spliced region with its background | 59 |
 cleanlab/cleanvision | Automatically detects issues in image datasets to improve computer vision models | 1,038 |
| bcmi/accessory-try-on-dataset-strat | Provides a dataset and tools for image composition via virtual try-on using accessory images and human faces/portraits. | 21 |
 nvidia/dataset_synthesizer | Generates synthetic images and associated data for training deep learning models | 574 |
 iigroup/mm-celeba-hq-dataset | A large-scale dataset for training and evaluating algorithms for text-driven face generation and understanding tasks. | 223 |
 imatge-upc/saliency-2016-cvpr | This project proposes a solution to predict salient areas in images using convolutional neural networks. | 186 |
 bonlime/keras-deeplab-v3-plus | An implementation of Deeplabv3+ in Keras with pretrained weights and customization options for semantic image segmentation. | 1,360 |
 lemondan/humanparsing-dataset | A collection of detailed pixel-wise annotations for fashion images used in human parsing research. | 213 |
 dib-lab/2012-paper-diginorm | Provides source code and analysis pipeline for evaluating an image normalization technique using publicly available data | 8 |