DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization

Ben, Xue; Ran, Shenghui; Chen, Quan; Jia, Rongfei; Zhao, Binqiang; Tang, Xing

doi:10.1007/978-3-031-20071-7_18

Cited by 38 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But the new Harmonizer makes the process of image harmonization explicit and easy to explain. Based on the HSV color model, Xue et al [4] proposed four neural color filters: value filter, saturation filter, hue filter and attentive rendering filter. This model is different from the traditional black box model.…”

Section: Color Curvementioning

confidence: 99%

See 1 more Smart Citation

The Way to picture Reality: A Review, Evaluation and Recipe of Image Harmonization

Tian

Hou

Zhang

2023

Preprint

View full text Add to dashboard Cite

Image harmonization is an interesting but challenging task in image processing. The task is to adjust the visual information between the foreground and background in the picture, so that the overall picture becomes a harmonious and unified process. Compared to traditional unsupervised methods for image processing, recent developments in deep learning have brought new opportunities to the field. Since 2019, related image harmonization papers have begun to appear on a large scale. In order to better sort out the development of this field, we summarize the field from two aspects of supervised learning and unsupervised learning, and also deeply integrate the existing image harmonization dataset and related index evaluation. We then conduct a detailed comparison and analysis of the existing models. Finally, the current challenges and future research directions of deep learning in image harmonization are discussed.

show abstract

Section: Color Curvementioning

confidence: 99%

“…2 iDIH-S[1], S in Extro info represents that auxiliary semantic information is used in model usage 3. The fMSE indicator in the iSSAM[1] results is tested with the network released by the official GitHub and the optimal parameters 4. The result test of[84] comes from the network and optimal parameters released by the official GitHub.…”

mentioning

confidence: 99%

The Way to picture Reality: A Review, Evaluation and Recipe of Image Harmonization

Tian

Hou

Zhang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…S 2 CRNet developed a colour- mapping curve from the foreground to the background and used it to render high-resolution images [22]. DCCF uses a low-resolution network to extract hue, saturation, value, and attentive rendering filters and applies these filters to the original image [23].…”

Section: Related Workmentioning

confidence: 99%

“…To address this issue, semantic information was introduced into the harmonisation network. However, some recent studies [13][14][15][16][17][18][19][20][21][22][23] did not consider the use of semantic features. Tsai et al [11] leveraged an extra branch to capture the contextual information of images; the semantic features passing through the harmonisation network were weakened by the common normalisation layers.…”

Section: Related Workmentioning

confidence: 99%

Semantic‐aware visual consistency network for fused image harmonisation

Huang

Zhu

et al. 2023

IET Signal Processing

View full text Add to dashboard Cite

With a focus on integrated sensing, communication, and computation (ISCC) systems, multiple sensor devices collect information of different objects and upload it to data processing servers for fusion. Appearance gaps in composite images caused by distinct capture conditions can degrade the visual quality and affect the accuracy of other image processing and analysis results. The authors propose a fused-image harmonisation method that aims to eliminate appearance gaps among different objects. First, the authors modify a lightweight image harmonisation backbone and combined it with a pretrained segmentation model, in which the extracted semantic features were fed to both the encoder and decoder. Then the authors implement a semantic-related background-toforeground style transfer by leveraging spatial separation adaptive instance normalisation (SAIN). To better preserve the input semantic information, the authors design a simple and effective semantic-aware adaptive denormalisation (SADE) module. Experimental results demonstrate that the authors' proposed method achieves competitive performance on the iHarmony4 dataset and benefits from the harmonisation of fused images with incompatible appearance gaps.

show abstract

“…We use PyTorch [25] to implement our models with Nvidia Tesla A100 GPUs. including DIH [31], S 2 AM [7], DoveNet [6], RainNet [21], Bargainnet [4], Intrinsic [11], D-HT [10], CDTNet [5], Harmonizer [15], DCCF [34] and S 2 CRNet [18].…”

Section: Experiments Settingmentioning

confidence: 99%

Hierarchical Dynamic Image Harmonization

Chen¹,

Gu²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image harmonization is a critical task in computer vision, which aims to adjust the fore-ground to make it compatible with the back-ground. Recent works mainly focus on using global transformation (i.e., normalization and color curve rendering) to achieve visual consistency. However, these model ignore local consistency and their model size limit their harmonization ability on edge devices. Inspired by the dynamic deep networks that adapt the model structures or parameters conditioned on the inputs, we propose a hierarchical dynamic network (HDNet) for efficient image harmonization to adapt the model parameters and features from local to global view for better feature transformation. Specifically, local dynamics (LD) and mask-aware global dynamics (MGD) are applied. LD enables features of different channels and positions to change adaptively and improve the representation ability of geometric transformation through structural information learning. MGD learns the representations of fore-and back-ground regions and correlations to global harmonization. Experiments show that the proposed HDNet reduces more than 80% parameters compared with previous methods but still achieves the state-of-the-art performance on the popular iHarmony4 dataset. Our code is avaliable in https://github. com/chenhaoxing/HDNet.

show abstract

DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization

Cited by 38 publications

References 30 publications

The Way to picture Reality: A Review, Evaluation and Recipe of Image Harmonization

The Way to picture Reality: A Review, Evaluation and Recipe of Image Harmonization

Semantic‐aware visual consistency network for fused image harmonisation

Hierarchical Dynamic Image Harmonization

Contact Info

Product

Resources

About