CcHarmony: Color-checker based Image Harmonization Dataset
- URL: http://arxiv.org/abs/2206.00800v1
- Date: Wed, 1 Jun 2022 23:57:16 GMT
- Title: CcHarmony: Color-checker based Image Harmonization Dataset
- Authors: Haoxu Huang, Li Niu
- Abstract summary: Image harmonization targets at adjusting the foreground in a composite image to make it compatible with the background, producing a more realistic and harmonious image.
We construct an image harmonization dataset called ccHarmony, which is named after color checker (cc)
- Score: 13.651034765401386
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Image harmonization targets at adjusting the foreground in a composite image
to make it compatible with the background, producing a more realistic and
harmonious image. Training deep image harmonization network requires abundant
training data, but it is extremely difficult to acquire training pairs of
composite images and ground-truth harmonious images. Therefore, existing works
turn to adjust the foreground appearance in a real image to create a synthetic
composite image. However, such adjustment may not faithfully reflect the
natural illumination change of foreground. In this work, we explore a novel
transitive way to construct image harmonization dataset. Specifically, based on
the existing datasets with recorded illumination information, we first convert
the foreground in a real image to the standard illumination condition, and then
convert it to another illumination condition, which is combined with the
original background to form a synthetic composite image. In this manner, we
construct an image harmonization dataset called ccHarmony, which is named after
color checker (cc). The dataset is available at
https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony.
Related papers
- Deep Image Harmonization with Learnable Augmentation [17.690945824240348]
Learnable augmentation is proposed to enrich the illumination diversity of small-scale datasets for better harmonization performance.
SycoNet takes in a real image with foreground mask and a random vector to learn suitable color transformation, which is applied to the foreground of this real image to produce a synthetic composite image.
arXiv Detail & Related papers (2023-08-01T08:40:23Z) - Deep Image Harmonization with Globally Guided Feature Transformation and
Relation Distillation [20.302430505018]
We show that using global information to guide foreground feature transformation could achieve significant improvement.
We also propose to transfer the foreground-background relation from real images to composite images, which can provide intermediate supervision for the transformed encoder features.
arXiv Detail & Related papers (2023-08-01T07:53:25Z) - Semi-supervised Parametric Real-world Image Harmonization [38.66826236220168]
Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo.
This simulated data does not model many of the important appearance mismatches between foreground and background in real composites.
We propose a new semi-supervised training strategy that addresses this problem and lets us learn complex local appearance harmonization from unpaired real composites.
arXiv Detail & Related papers (2023-03-01T01:09:01Z) - Image Harmonization with Region-wise Contrastive Learning [51.309905690367835]
We propose a novel image harmonization framework with external style fusion and region-wise contrastive learning scheme.
Our method attempts to bring together corresponding positive and negative samples by maximizing the mutual information between the foreground and background styles.
arXiv Detail & Related papers (2022-05-27T15:46:55Z) - FRIH: Fine-grained Region-aware Image Harmonization [49.420765789360836]
We propose a novel global-local two stages framework for Fine-grained Region-aware Image Harmonization (FRIH)
Our algorithm achieves the best performance on iHarmony4 dataset (PSNR is 38.19 dB) with a lightweight model.
arXiv Detail & Related papers (2022-05-13T04:50:26Z) - Interactive Portrait Harmonization [99.15331091722231]
Current image harmonization methods consider the entire background as the guidance for harmonization.
A new flexible framework that allows users to pick certain regions of the background image and use it to guide the harmonization is proposed.
Inspired by professional portrait harmonization users, we also introduce a new luminance matching loss to optimally match the color/luminance conditions between the composite foreground and select reference region.
arXiv Detail & Related papers (2022-03-15T19:30:34Z) - Enhancing Low-Light Images in Real World via Cross-Image Disentanglement [58.754943762945864]
We propose a new low-light image enhancement dataset consisting of misaligned training images with real-world corruptions.
Our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.
arXiv Detail & Related papers (2022-01-10T03:12:52Z) - Spatial-Separated Curve Rendering Network for Efficient and
High-Resolution Image Harmonization [59.19214040221055]
We propose a novel spatial-separated curve rendering network (S$2$CRNet) for efficient and high-resolution image harmonization.
The proposed method reduces more than 90% parameters compared with previous methods.
Our method can work smoothly on higher resolution images in real-time which is more than 10$times$ faster than the existing methods.
arXiv Detail & Related papers (2021-09-13T07:20:16Z) - SSH: A Self-Supervised Framework for Image Harmonization [97.16345684998788]
We propose a novel Self-Supervised Harmonization framework (SSH) that can be trained using just "free" natural images without being edited.
Our results show that the proposedSSH outperforms previous state-of-the-art methods in terms of reference metrics, visual quality, and subject user study.
arXiv Detail & Related papers (2021-08-15T19:51:33Z) - Region-aware Adaptive Instance Normalization for Image Harmonization [14.77918186672189]
To acquire photo-realistic composite images, one must adjust the appearance and visual style of the foreground to be compatible with the background.
Existing deep learning methods for harmonizing composite images directly learn an image mapping network from the composite to the real one.
We propose a Region-aware Adaptive Instance Normalization (RAIN) module, which explicitly formulates the visual style from the background and adaptively applies them to the foreground.
arXiv Detail & Related papers (2021-06-05T09:57:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.