Learning SAR-to-Optical Image Translation via Diffusion Models with Color Memory

Z Guo, J Liu, Q Cai, Z Zhang… - IEEE Journal of Selected …, 2024 - ieeexplore.ieee.org
Synthetic aperture radar (SAR) and optical sensing are two important means of Earth
observation. SAR-to-optical image translation (S2OIT) can integrate the advantages of both …

Advanced Deep Learning Techniques for High-Quality Synthetic Thermal Image Generation

V Pavez, G Hermosilla, M Silva, G Farias - Mathematics, 2023 - mdpi.com
In this paper, we introduce a cutting-edge system that leverages state-of-the-art deep
learning methodologies to generate high-quality synthetic thermal face images. Our unique …

Survey on controlable image synthesis with deep learning

S Zhang, J Li, L Yang - arxiv preprint arxiv:2307.10275, 2023 - arxiv.org
Image synthesis has attracted emerging research interests in academic and industry
communities. Deep learning technologies especially the generative models greatly inspired …

MS-GAN: Learn to Memorize Scene for Unpaired SAR-to-Optical Image Translation

Z Guo, Z Zhang, Q Cai, J Liu, Y Fan… - IEEE Journal of Selected …, 2024 - ieeexplore.ieee.org
Synthetic aperture radar (SAR) and optical sensing are two important means of Earth
observation. SAR-to-optical image translation (S2OIT) can integrate the advantages of both …

MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering

A AlMughrabi, R Marques, P Radeva - arxiv preprint arxiv:2407.02668, 2024 - arxiv.org
We propose MomentsNeRF, a novel framework for one-and few-shot neural rendering that
predicts a neural representation of a 3D scene using Orthogonal Moments. Our architecture …

Melanoma classification using generative adversarial network and proximal policy optimization

X Ju, CH Lin, S Lee, S Wei - Photochemistry and Photobiology, 2024 - Wiley Online Library
In oncology, melanoma is a serious concern, often arising from DNA changes caused mainly
by ultraviolet radiation. This cancer is known for its aggressive growth, highlighting the …

Latent-SDE: guiding stochastic differential equations in latent space for unpaired image-to-image translation

X Zhang, M Li, Y He, Y Gou, Y Zhang - Complex & Intelligent Systems, 2024 - Springer
Score-based diffusion models have shown promising results in unpaired image-to-image
translation (I2I). However, the existing methods only perform unpaired I2I in pixel space …

[HTML][HTML] Survey on low-level controllable image synthesis with deep learning

S Zhang, J Li, L Yang - Electronic Research Archive, 2023 - aimspress.com
Deep learning, particularly generative models, has inspired controllable image synthesis
methods and applications. These approaches aim to generate specific visual content using …

Robust and Controllable Generative Models by Leveraging Physics-Based, Probabilistic, and Geometric Methods

R Singh - 2023 - search.proquest.com
Generative models are deep neural network-based models trained to learn the underlying
distribution of a dataset. Once trained, these models can be used to sample novel data …