Nested Scale-Editing for Conditional Image Synthesis

Zhang, Lingzhi; Wang, Jiancong; Xu, Yinshuang; Min, Jie; Wen, Tarmily; Gee, James C.; Shi, Jianbo

doi:10.1109/cvpr42600.2020.00552

Cited by 6 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extraction of semantic information also becomes rich. Zhang et al [38] proposed semantic persistence across scales by sharing common latent codes, and scale independence is achieved by nesting scale disentanglement losses. Scale-specific diversity is created by incorporating progressive diversity constraints.…”

Section: Vanilla Modelsmentioning

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

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: Vanilla Modelsmentioning

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

“…Much of the I2I research focuses on filling in missing pixels, i.e, image inpainting [14], [15], [16], [17], [18] and image outpainting [189], but they treat different occluded images. Taking the image of a human face as an example, the image inpainting task produces visually realistic and semantically correct results from the input with a masked nose, mouth and eyes, while the image outpainting task translates a highly occluded face image that only has a nose, mouth and eyes.…”

Section: Applicationmentioning

confidence: 99%

Image-to-Image Translation: Methods and Applications

Pang¹,

Lin²,

Qin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations. I2I has drawn increasing attention and made tremendous progress in recent years because of its wide range of applications in many computer vision and image processing problems, such as image synthesis, segmentation, style transfer, restoration, and pose estimation. In this paper, we provide an overview of the I2I works developed in recent years.We will analyze the key techniques of the existing I2I works and clarify the main progress the community has made. Additionally, we will elaborate on the effect of I2I on the research and industry community and point out remaining challenges in related fields.Index Terms-image-to-image translation, two-domain I2I, multi-domain I2I, supervised methods, unsupersived methods, semi-supervised methods, few-shot methods Yingxue Pang, Jianxin Lin, and Zhibo Chen are with the De-

show abstract

“…Generating high-resolution images that semantically consistent with various input types is a frontier but challenging task. It has tremendous practical applications, such as intelligent image editing [38], game generation [12], and face representation interpreting [29]. Recently, thanks to the generative adversarial networks (GANs), which have been at the helm of remarkable advances in image synthesis, GAN-based image generation methods [11,24,2] greatly drive research progress in multi-modal feature learning and visual distribution modeling.…”

mentioning

confidence: 99%

Global-Affine and Local-Specific Generative Adversarial Network for semantic-guided image generation

Zhang¹,

Ni²,

Hou³

et al. 2021

MFC

View full text Add to dashboard Cite

The recent progress in learning image feature representations has opened the way for tasks such as label-to-image or text-to-image synthesis. However, one particular challenge widely observed in existing methods is the difficulty of synthesizing fine-grained textures and small-scale instances. In this paper, we propose a novel Global-Affine and Local-Specific Generative Adversarial Network (GALS-GAN) to explicitly construct global semantic layouts and learn distinct instance-level features. To achieve this, we adopt the graph convolutional network to calculate the instance locations and spatial relationships from scene graphs, which allows our model to obtain the highfidelity semantic layouts. Also, a local-specific generator, where we introduce the feature filtering mechanism to separately learn semantic maps for different categories, is utilized to disentangle and generate specific visual features. Moreover, we especially apply a weight map predictor to better combine the global and local pathways considering the highly complementary between these two generation sub-networks. Extensive experiments on the COCO-Stuff and Visual Genome datasets demonstrate the superior generation performance of our model against previous methods, our approach is more capable of capturing photo-realistic local characteristics and rendering small-sized entities with more details.

show abstract

Nested Scale-Editing for Conditional Image Synthesis

Cited by 6 publications

References 37 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

Image-to-Image Translation: Methods and Applications

Global-Affine and Local-Specific Generative Adversarial Network for semantic-guided image generation

Contact Info

Product

Resources

About