Spectral super-resolution meets deep learning: Achievements and challenges
Spectral super-resolution (sSR) is a very important technique to obtain hyperspectral images
from only RGB images, which can effectively overcome the high acquisition cost and low …
from only RGB images, which can effectively overcome the high acquisition cost and low …
LKAT-GAN: a GAN for thermal infrared image colorization based on large kernel and attentionunet-transformer
Y He, X Jin, Q Jiang, Z Cheng… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Because thermal infrared (TIR) images are not affected by light and foggy environments,
which are widely used in various night traffic scenarios. Especially, thermal infrared images …
which are widely used in various night traffic scenarios. Especially, thermal infrared images …
Colorizing the past: Deep learning for the automatic colorization of historical aerial images
EM Farella, S Malek, F Remondino - Journal of Imaging, 2022 - mdpi.com
The colorization of grayscale images can, nowadays, take advantage of recent progress and
the automation of deep-learning techniques. From the media industry to medical or …
the automation of deep-learning techniques. From the media industry to medical or …
An unpaired thermal infrared image translation method using GMA-CycleGAN
S Yang, M Sun, X Lou, H Yang, H Zhou - Remote Sensing, 2023 - mdpi.com
Automatically translating chromaticity-free thermal infrared (TIR) images into realistic color
visible (CV) images is of great significance for autonomous vehicles, emergency rescue …
visible (CV) images is of great significance for autonomous vehicles, emergency rescue …
Pareto invariant representation learning for multimedia recommendation
Multimedia recommendation involves personalized ranking tasks, where multimedia content
is usually represented using a generic encoder. However, these generic representations …
is usually represented using a generic encoder. However, these generic representations …
CoColor: Interactive exploration of color designs
Choosing colors is a pivotal but challenging component of graphic design. The paper
presents an intelligent interaction technique supporting designers' creativity in color design …
presents an intelligent interaction technique supporting designers' creativity in color design …
Deep transfer learning-based adaptive gesture recognition of a soft e-skin patch with reduced training data and time
Y Rong, G Gu - Sensors and Actuators A: Physical, 2023 - Elsevier
Deep learning-based classification algorithms are promising in gesture recognition with soft
e-skin patches. However, the reported algorithms usually require large amount of training …
e-skin patches. However, the reported algorithms usually require large amount of training …
Preserving structural consistency in arbitrary artist and artwork style transfer
Deep generative models are effective in style transfer. Previous methods learn one or
several specific artist-style from a collection of artworks. These methods not only …
several specific artist-style from a collection of artworks. These methods not only …
AutoCaCoNet: Automatic Cartoon Colorization Network using self-attention GAN, segmentation, and color correction
Colorization is a captivating research area within the realm of computer vision. Conventional
methods often rely on object-based strategies, necessitating access to extensive image …
methods often rely on object-based strategies, necessitating access to extensive image …
Texture-aware gray-scale image colorization using a bistream generative adversarial network with multi scale attention structure
S Zang, M Chen, Z Ai, J Chi, G Yang, C Chen… - … Applications of Artificial …, 2023 - Elsevier
Various methods based on deep neural networks have been proposed to generate color
images from gray-scale images, meanwhile, Generative adversarial networks (GANs) are …
images from gray-scale images, meanwhile, Generative adversarial networks (GANs) are …