Generative Adversarial Networks in the built environment: A comprehensive review of the application of GANs across data types and scales

AN Wu, R Stouffs, F Biljecki - Building and Environment, 2022‏ - Elsevier
Abstract Generative Adversarial Networks (GANs) are a type of deep neural network that
have achieved many state-of-the-art results for generative tasks. GANs can be useful in the …

A comprehensive review of past and present image inpainting methods

J Jam, C Kendrick, K Walker, V Drouard… - Computer vision and …, 2021‏ - Elsevier
Images can be described as visual representations or likeness of something (person or
object) which can be reproduced or captured, eg a hand drawing, photographic material …

DNNAM: Image inpainting algorithm via deep neural networks and attention mechanism

Y Chen, R **a, K Yang, K Zou - Applied Soft Computing, 2024‏ - Elsevier
Most image inpainting algorithms have problems such as fuzzy images, texture distortion
and semantic inaccuracy, and the image inpainting effect is limited when processing photos …

Image inpainting via conditional texture and structure dual generation

X Guo, H Yang, D Huang - Proceedings of the IEEE/CVF …, 2021‏ - openaccess.thecvf.com
Deep generative approaches have recently made considerable progress in image
inpainting by introducing structure priors. Due to the lack of proper interaction with image …

MFMAM: Image inpainting via multi-scale feature module with attention module

Y Chen, R **a, K Yang, K Zou - Computer Vision and Image Understanding, 2024‏ - Elsevier
Currently, most image inpainting algorithms based on deep learning cause information loss
when acquiring deep level features. It is not conducive to the image inpainting of texture …

Recurrent feature reasoning for image inpainting

J Li, N Wang, L Zhang, B Du… - Proceedings of the IEEE …, 2020‏ - openaccess.thecvf.com
Existing inpainting methods have achieved promising performance for recovering regular or
small image defects. However, filling in large continuous holes remains difficult due to the …

PSCC-Net: Progressive spatio-channel correlation network for image manipulation detection and localization

X Liu, Y Liu, J Chen, X Liu - … on Circuits and Systems for Video …, 2022‏ - ieeexplore.ieee.org
To defend against manipulation of image content, such as splicing, copy-move, and
removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to …

Image inpainting with local and global refinement

W Quan, R Zhang, Y Zhang, Z Li… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Image inpainting has made remarkable progress with recent advances in deep learning.
Popular networks mainly follow an encoder-decoder architecture (sometimes with skip …

[HTML][HTML] DARGS: Image inpainting algorithm via deep attention residuals group and semantics

Y Chen, R **a, K Yang, K Zou - Journal of King Saud University-Computer …, 2023‏ - Elsevier
To solving the problems that the existing image inpainting methods lack authenticity, do not
deal with the information of missing and non-missing regions flexibly, and do not deal with …

Uni-paint: A unified framework for multimodal image inpainting with pretrained diffusion model

S Yang, X Chen, J Liao - Proceedings of the 31st ACM International …, 2023‏ - dl.acm.org
Recently, text-to-image denoising diffusion probabilistic models (DDPMs) have
demonstrated impressive image generation capabilities and have also been successfully …