SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing

Shi, Jing; Xu, Ning; Zheng, Haitian; Smith, Alex; Luo, Jiebo; Xu, Chenliang

doi:10.1109/cvpr52688.2022.01911

Cited by 15 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where 1 represents the all-1 matrix that has the same shape as M. And the mask update strategy is shown in Equation (3).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Image inpainting network based on multi‐level attention mechanism

Xiang,

Min,

Wei

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Image inpainting networks based on deep learning techniques have been widely used in many important fields. However, most inpainting networks fail to generate desirable repaired images. This may be due to their failure to extract effective features and accurately assign high weights to the undamaged regions. To alleviate these problems, an image inpainting network based on gated convolution and multi‐level attention mechanism (IIN‐GCMAM) is proposed in this paper. This network follows encoder–decoder architecture, consisting of the gated convolution encoder (GC‐encoder) and the multi‐level attention mechanism decoder (MAM‐decoder). The GC‐encoder weighs the extracted features with gated convolutions, which reduces the interference caused by the damaged regions. The multi‐level attention mechanism employed in the MAM‐decoder uses multi‐scale feature maps spatially and channel‐wise to improve the consistency in global structure and the fineness of repaired results. Extensive experiments are conducted on the common datasets, Paris StreetView and CelebA. Experimental results indicate that the proposed IIN‐GCMAM can achieve a good performance on the common evaluation metrics and visual effects. It can achieve 0.0408, 0.720, and 22.27 in MAE, SSIM, and PSNR at the mask ratio of 50%–60%, respectively.

show abstract

“…where 1 represents the all-1 matrix that has the same shape as M. And the mask update strategy is shown in Equation (3).…”

Section: Related Workmentioning

confidence: 99%

“…The goal of image inpainting is to make the repaired results closer to the ground truth in terms of evaluation metrics and visual effects. Image inpainting networks are widely used in many fields, such as image editing, unwanted object removal image super-resolution and image zooming, etc [1][2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Image inpainting network based on multi‐level attention mechanism

Xiang,

Min,

Wei

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Pre-information GAN models Shi et al [56] proposed a unified model for open-domain image editing. Through the extraction and adjustment of color information in the image, the original structural information of the image is not lost.…”

Section: Image Fusion Gan 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

“…Although photorealistic images were harvested, fine-grained problems (artifacts and substandard textures) at high resolution were exposed. Around StyleGAN, different mapping methods [28,29,30,31] all yield highfidelity face images full of details and structural integrity; [32,33,34,35] try to make the editing of GAN controllable by dissecting the latent variables.…”

Section: Conditional Informationmentioning

confidence: 99%

Embedding diverse features in latent space for face attribute editing

Yuan

et al. 2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

Face attribute editing, one of the important research directions in face image synthesis and processing techniques, aims to photorealistic editing single or multiple attributes of face images on demand using editing and generation models. Most existing methods are based on generative adversarial networks, using target attribute vectors to control the editing region or Gaussian noise as conditional input to capture texture details. However, these cannot better control the consistency of attributes in irrelevant regions, while the generation of fidelity is also limited. In this paper, we propose a method that uses an optimized latent space to fuse the attribute feature maps into the latent space. At the same time, make full use of the conditional information for additional constraints. Then, in the image generation phase, we use a progressive architecture for controlled editing of face attributes at different granularities. At last, we also conducted an ablation study on the selected training scheme further to demonstrate the stability and accuracy of our chosen method. The experiments show that our proposed approach, using an end-to-end progressive image translation network architecture, obtained qualitative (FID) as well as quantitative (LPIPS) face image editing results.

show abstract

SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing

Cited by 15 publications

References 24 publications

Image inpainting network based on multi‐level attention mechanism

Image inpainting network based on multi‐level attention mechanism

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

Embedding diverse features in latent space for face attribute editing

Contact Info

Product

Resources

About