A complete survey on generative ai (aigc): Is chatgpt from gpt-4 to gpt-5 all you need?

C Zhang, C Zhang, S Zheng, Y Qiao, C Li… - arxiv preprint arxiv …, 2023 - arxiv.org
As ChatGPT goes viral, generative AI (AIGC, aka AI-generated content) has made headlines
everywhere because of its ability to analyze and create text, images, and beyond. With such …

Mat: Mask-aware transformer for large hole image inpainting

W Li, Z Lin, K Zhou, L Qi, Y Wang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Recent studies have shown the importance of modeling long-range interactions in the
inpainting problem. To achieve this goal, existing approaches exploit either standalone …

Pd-gan: Probabilistic diverse gan for image inpainting

H Liu, Z Wan, W Huang, Y Song… - Proceedings of the …, 2021 - openaccess.thecvf.com
We propose PD-GAN, a probabilistic diverse GAN forimage inpainting. Given an input image
with arbitrary holeregions, PD-GAN produces multiple inpainting results withdiverse and …

[HTML][HTML] Machine learning and deep learning applications-a vision

N Sharma, R Sharma, N **dal - Global Transitions Proceedings, 2021 - Elsevier
The application of artificial intelligence is machine learning which is one of the current topics
in the computer field as well as for the new COVID-19 pandemic. Researchers have given a …

High-fidelity pluralistic image completion with transformers

Z Wan, J Zhang, D Chen, J Liao - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Image completion has made tremendous progress with convolutional neural networks
(CNNs), because of their powerful texture modeling capacity. However, due to some …

Blind image super-resolution: A survey and beyond

A Liu, Y Liu, J Gu, Y Qiao… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Blind image super-resolution (SR), aiming to super-resolve low-resolution images with
unknown degradation, has attracted increasing attention due to its significance in promoting …

Reduce information loss in transformers for pluralistic image inpainting

Q Liu, Z Tan, D Chen, Q Chu, X Dai… - Proceedings of the …, 2022 - openaccess.thecvf.com
Transformers have achieved great success in pluralistic image inpainting recently. However,
we find existing transformer based solutions regard each pixel as a token, thus suffer from …

Preserving Artistic Heritage: A Comprehensive Review of Virtual Restoration Methods for Damaged Artworks

P Kumar, V Gupta - Archives of Computational Methods in Engineering, 2024 - Springer
Restoration of damaged artwork is an important task to preserve the culture and history of
humankind. Restoration of damaged artwork is a delicate, complex, and irreversible process …

Bringing old films back to life

Z Wan, B Zhang, D Chen, J Liao - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
We present a learning-based framework, recurrent transformer network (RTN), to restore
heavily degraded old films. Instead of performing frame-wise restoration, our method is …

Generating synthetic mixed-type longitudinal electronic health records for artificial intelligent applications

J Li, BJ Cairns, J Li, T Zhu - NPJ Digital Medicine, 2023 - nature.com
The recent availability of electronic health records (EHRs) have provided enormous
opportunities to develop artificial intelligence (AI) algorithms. However, patient privacy has …