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 …

[HTML][HTML] Deep learning in computer vision: A critical review of emerging techniques and application scenarios

J Chai, H Zeng, A Li, EWT Ngai - Machine Learning with Applications, 2021 - Elsevier
Deep learning has been overwhelmingly successful in computer vision (CV), natural
language processing, and video/speech recognition. In this paper, our focus is on CV. We …

Beyond brightening low-light images

Y Zhang, X Guo, J Ma, W Liu, J Zhang - International Journal of Computer …, 2021 - Springer
Images captured under low-light conditions often suffer from (partially) poor visibility.
Besides unsatisfactory lightings, multiple types of degradation, such as noise and color …

Deep learning for image inpainting: A survey

H Xiang, Q Zou, MA Nawaz, X Huang, F Zhang, H Yu - Pattern Recognition, 2023 - Elsevier
Image inpainting has been widely exploited in the field of computer vision and image
processing. The main purpose of image inpainting is to produce visually plausible structure …

Artificial intelligence in the creative industries: a review

N Anantrasirichai, D Bull - Artificial intelligence review, 2022 - Springer
This paper reviews the current state of the art in artificial intelligence (AI) technologies and
applications in the context of the creative industries. A brief background of AI, and …

Kindling the darkness: A practical low-light image enhancer

Y Zhang, J Zhang, X Guo - Proceedings of the 27th ACM international …, 2019 - dl.acm.org
Images captured under low-light conditions often suffer from (partially) poor visibility.
Besides unsatisfactory lightings, multiple types of degradations, such as noise and color …

Large scale image completion via co-modulated generative adversarial networks

S Zhao, J Cui, Y Sheng, Y Dong, X Liang… - arXiv preprint arXiv …, 2021 - arxiv.org
Numerous task-specific variants of conditional generative adversarial networks have been
developed for image completion. Yet, a serious limitation remains that all existing algorithms …

Brief review of image denoising techniques

L Fan, F Zhang, H Fan, C Zhang - Visual Computing for Industry …, 2019 - Springer
With the explosion in the number of digital images taken every day, the demand for more
accurate and visually pleasing images is increasing. However, the images captured by …

Nbnet: Noise basis learning for image denoising with subspace projection

S Cheng, Y Wang, H Huang, D Liu… - Proceedings of the …, 2021 - openaccess.thecvf.com
In this paper, we introduce NBNet, a novel framework for image denoising. Unlike previous
works, we propose to tackle this challenging problem from a new perspective: noise …

Fixing the train-test resolution discrepancy

H Touvron, A Vedaldi, M Douze… - Advances in neural …, 2019 - proceedings.neurips.cc
Data-augmentation is key to the training of neural networks for image classification. This
paper first shows that existing augmentations induce a significant discrepancy between the …